diff --git "a/train.log" "b/train.log"
--- "a/train.log"
+++ "b/train.log"
@@ -7167,3 +7167,4226 @@ Eval results for step (5000 / 100000 | Eval Loss: 1.7768317461013794 | Eval wer:
 
 60%|██████    | 3/5 [02:21<01:10, 35.20s/it]
 
 80%|████████  | 4/5 [02:22<00:21, 21.58s/it]
 
100%|██████████| 5/5 [02:23<00:00, 14.07s/it]
100%|██████████| 5/5 [02:23<00:00, 28.65s/it]
+
+
+
Evaluating eval...:   0%|          | 0/1900 [00:00<?, ?it/s]
+
+
Evaluating eval...:   0%|          | 1/1900 [00:03<1:43:20,  3.27s/it]
+
+
Evaluating eval...:   0%|          | 2/1900 [00:04<1:04:43,  2.05s/it]
+
+
Evaluating eval...:   0%|          | 3/1900 [00:05<53:12,  1.68s/it]  
+
+
Evaluating eval...:   0%|          | 4/1900 [00:06<47:32,  1.50s/it]
+
+
Evaluating eval...:   0%|          | 5/1900 [00:08<43:39,  1.38s/it]
+
+
Evaluating eval...:   0%|          | 6/1900 [00:09<41:17,  1.31s/it]
+
+
Evaluating eval...:   0%|          | 7/1900 [00:10<39:59,  1.27s/it]
+
+
Evaluating eval...:   0%|          | 8/1900 [00:11<38:56,  1.23s/it]
+
+
Evaluating eval...:   0%|          | 9/1900 [00:12<37:56,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 10/1900 [00:13<38:04,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 11/1900 [00:15<38:17,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 12/1900 [00:16<38:07,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 13/1900 [00:17<38:04,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 14/1900 [00:18<37:42,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 15/1900 [00:20<37:49,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 16/1900 [00:21<37:48,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 17/1900 [00:22<38:20,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 18/1900 [00:23<38:07,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 19/1900 [00:24<37:24,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 20/1900 [00:26<37:40,  1.20s/it]
+
+
Evaluating eval...:   1%|          | 21/1900 [00:27<38:27,  1.23s/it]
+
+
Evaluating eval...:   1%|          | 22/1900 [00:28<37:49,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 23/1900 [00:29<37:15,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 24/1900 [00:30<37:14,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 25/1900 [00:31<36:40,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 26/1900 [00:33<36:26,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 27/1900 [00:34<36:53,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 28/1900 [00:35<36:45,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 29/1900 [00:36<36:43,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 30/1900 [00:37<36:39,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 31/1900 [00:39<36:35,  1.17s/it]
+
+
Evaluating eval...:   2%|▏         | 32/1900 [00:40<36:35,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 33/1900 [00:41<36:48,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 34/1900 [00:42<37:15,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 35/1900 [00:43<37:41,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 36/1900 [00:45<38:14,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 37/1900 [00:46<37:57,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 38/1900 [00:47<37:37,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 39/1900 [00:48<37:25,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 40/1900 [00:49<37:17,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 41/1900 [00:51<36:52,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 42/1900 [00:52<37:43,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 43/1900 [00:53<37:25,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 44/1900 [00:54<37:24,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 45/1900 [00:55<36:47,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 46/1900 [00:57<36:31,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 47/1900 [00:58<36:05,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 48/1900 [00:59<35:53,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 49/1900 [01:00<35:45,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 50/1900 [01:01<36:08,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 51/1900 [01:02<36:14,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 52/1900 [01:04<36:05,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 53/1900 [01:05<36:00,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 54/1900 [01:06<36:34,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 55/1900 [01:07<37:00,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 56/1900 [01:08<37:12,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 57/1900 [01:10<37:00,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 58/1900 [01:11<37:00,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 59/1900 [01:12<36:50,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 60/1900 [01:13<36:12,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 61/1900 [01:14<37:31,  1.22s/it]
+
+
Evaluating eval...:   3%|▎         | 62/1900 [01:16<36:58,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 63/1900 [01:17<36:38,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 64/1900 [01:18<36:28,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 65/1900 [01:19<36:07,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 66/1900 [01:20<35:54,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 67/1900 [01:21<35:45,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 68/1900 [01:23<37:18,  1.22s/it]
+
+
Evaluating eval...:   4%|▎         | 69/1900 [01:24<36:31,  1.20s/it]
+
+
Evaluating eval...:   4%|▎         | 70/1900 [01:25<36:47,  1.21s/it]
+
+
Evaluating eval...:   4%|▎         | 71/1900 [01:26<36:47,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 72/1900 [01:28<37:23,  1.23s/it]
+
+
Evaluating eval...:   4%|▍         | 73/1900 [01:29<37:08,  1.22s/it]
+
+
Evaluating eval...:   4%|▍         | 74/1900 [01:30<36:50,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 75/1900 [01:31<36:20,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 76/1900 [01:32<36:04,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 77/1900 [01:34<36:07,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 78/1900 [01:35<36:08,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 79/1900 [01:36<36:09,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 80/1900 [01:37<36:03,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 81/1900 [01:38<35:41,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 82/1900 [01:40<36:25,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 83/1900 [01:41<36:31,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 84/1900 [01:42<36:22,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 85/1900 [01:43<36:11,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 86/1900 [01:44<35:32,  1.18s/it]
+
+
Evaluating eval...:   5%|▍         | 87/1900 [01:45<35:53,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 88/1900 [01:47<35:53,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 89/1900 [01:49<45:13,  1.50s/it]
+
+
Evaluating eval...:   5%|▍         | 90/1900 [01:50<42:09,  1.40s/it]
+
+
Evaluating eval...:   5%|▍         | 91/1900 [01:51<40:28,  1.34s/it]
+
+
Evaluating eval...:   5%|▍         | 92/1900 [01:52<38:42,  1.28s/it]
+
+
Evaluating eval...:   5%|▍         | 93/1900 [01:54<37:45,  1.25s/it]
+
+
Evaluating eval...:   5%|▍         | 94/1900 [01:55<36:42,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 95/1900 [01:56<35:54,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 96/1900 [01:57<36:36,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 97/1900 [01:58<35:50,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 98/1900 [02:00<36:04,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 99/1900 [02:01<35:44,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 100/1900 [02:02<35:33,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 101/1900 [02:03<36:53,  1.23s/it]
+
+
Evaluating eval...:   5%|▌         | 102/1900 [02:04<37:13,  1.24s/it]
+
+
Evaluating eval...:   5%|▌         | 103/1900 [02:06<36:37,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 104/1900 [02:07<36:22,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 105/1900 [02:08<36:05,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 106/1900 [02:09<35:28,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 107/1900 [02:10<36:08,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 108/1900 [02:12<35:26,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 109/1900 [02:13<35:44,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 110/1900 [02:14<35:17,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 111/1900 [02:15<35:43,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 112/1900 [02:16<36:39,  1.23s/it]
+
+
Evaluating eval...:   6%|▌         | 113/1900 [02:18<36:07,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 114/1900 [02:19<35:32,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 115/1900 [02:20<35:20,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 116/1900 [02:21<35:03,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 117/1900 [02:22<34:44,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 118/1900 [02:23<35:10,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 119/1900 [02:25<34:58,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 120/1900 [02:26<35:42,  1.20s/it]
+
+
Evaluating eval...:   6%|▋         | 121/1900 [02:27<35:13,  1.19s/it]
+
+
Evaluating eval...:   6%|▋         | 122/1900 [02:28<35:14,  1.19s/it]
+
+
Evaluating eval...:   6%|▋         | 123/1900 [02:29<35:04,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 124/1900 [02:31<35:23,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 125/1900 [02:32<35:50,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 126/1900 [02:33<36:31,  1.24s/it]
+
+
Evaluating eval...:   7%|▋         | 127/1900 [02:34<36:33,  1.24s/it]
+
+
Evaluating eval...:   7%|▋         | 128/1900 [02:36<35:50,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 129/1900 [02:37<35:16,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 130/1900 [02:38<34:56,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 131/1900 [02:39<34:59,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 132/1900 [02:40<35:43,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 133/1900 [02:42<35:01,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 134/1900 [02:43<35:07,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 135/1900 [02:44<35:16,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 136/1900 [02:45<35:41,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 137/1900 [02:46<36:22,  1.24s/it]
+
+
Evaluating eval...:   7%|▋         | 138/1900 [02:48<35:52,  1.22s/it]
+
+
Evaluating eval...:   7%|▋         | 139/1900 [02:49<35:20,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 140/1900 [02:50<35:36,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 141/1900 [02:51<35:21,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 142/1900 [02:52<35:49,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 143/1900 [02:54<35:50,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 144/1900 [02:55<35:00,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 145/1900 [02:56<35:14,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 146/1900 [02:57<34:51,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 147/1900 [02:58<35:17,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 148/1900 [03:00<34:37,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 149/1900 [03:01<34:43,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 150/1900 [03:02<36:12,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 151/1900 [03:03<35:38,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 152/1900 [03:05<35:34,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 153/1900 [03:06<36:08,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 154/1900 [03:07<35:44,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 155/1900 [03:08<35:17,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 156/1900 [03:09<34:50,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 157/1900 [03:11<36:35,  1.26s/it]
+
+
Evaluating eval...:   8%|▊         | 158/1900 [03:12<36:07,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 159/1900 [03:13<35:11,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 160/1900 [03:14<34:59,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 161/1900 [03:16<35:43,  1.23s/it]
+
+
Evaluating eval...:   9%|▊         | 162/1900 [03:17<35:00,  1.21s/it]
+
+
Evaluating eval...:   9%|▊         | 163/1900 [03:18<34:37,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 164/1900 [03:19<34:47,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 165/1900 [03:20<34:58,  1.21s/it]
+
+
Evaluating eval...:   9%|▊         | 166/1900 [03:22<34:36,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 167/1900 [03:23<35:28,  1.23s/it]
+
+
Evaluating eval...:   9%|▉         | 168/1900 [03:24<34:51,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 169/1900 [03:25<34:35,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 170/1900 [03:26<34:17,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 171/1900 [03:28<34:04,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 172/1900 [03:29<34:20,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 173/1900 [03:30<34:28,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 174/1900 [03:31<34:47,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 175/1900 [03:32<34:18,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 176/1900 [03:34<33:51,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 177/1900 [03:36<43:22,  1.51s/it]
+
+
Evaluating eval...:   9%|▉         | 178/1900 [03:37<40:53,  1.42s/it]
+
+
Evaluating eval...:   9%|▉         | 179/1900 [03:38<38:40,  1.35s/it]
+
+
Evaluating eval...:   9%|▉         | 180/1900 [03:39<37:27,  1.31s/it]
+
+
Evaluating eval...:  10%|▉         | 181/1900 [03:41<36:36,  1.28s/it]
+
+
Evaluating eval...:  10%|▉         | 182/1900 [03:42<37:01,  1.29s/it]
+
+
Evaluating eval...:  10%|▉         | 183/1900 [03:43<36:15,  1.27s/it]
+
+
Evaluating eval...:  10%|▉         | 184/1900 [03:44<35:19,  1.24s/it]
+
+
Evaluating eval...:  10%|▉         | 185/1900 [03:45<34:56,  1.22s/it]
+
+
Evaluating eval...:  10%|▉         | 186/1900 [03:47<34:22,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 187/1900 [03:48<34:44,  1.22s/it]
+
+
Evaluating eval...:  10%|▉         | 188/1900 [03:49<34:49,  1.22s/it]
+
+
Evaluating eval...:  10%|▉         | 189/1900 [03:50<34:15,  1.20s/it]
+
+
Evaluating eval...:  10%|█         | 190/1900 [03:51<34:06,  1.20s/it]
+
+
Evaluating eval...:  10%|█         | 191/1900 [03:53<34:02,  1.20s/it]
+
+
Evaluating eval...:  10%|█         | 192/1900 [03:54<35:04,  1.23s/it]
+
+
Evaluating eval...:  10%|█         | 193/1900 [03:55<35:37,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 194/1900 [03:57<35:33,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 195/1900 [03:58<35:31,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 196/1900 [03:59<34:59,  1.23s/it]
+
+
Evaluating eval...:  10%|█         | 197/1900 [04:00<35:56,  1.27s/it]
+
+
Evaluating eval...:  10%|█         | 198/1900 [04:02<36:05,  1.27s/it]
+
+
Evaluating eval...:  10%|█         | 199/1900 [04:03<35:09,  1.24s/it]
+
+
Evaluating eval...:  11%|█         | 200/1900 [04:04<34:34,  1.22s/it]
+
+
Evaluating eval...:  11%|█         | 201/1900 [04:05<34:05,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 202/1900 [04:06<33:34,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 203/1900 [04:07<33:36,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 204/1900 [04:09<33:34,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 205/1900 [04:10<33:36,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 206/1900 [04:11<33:39,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 207/1900 [04:12<34:20,  1.22s/it]
+
+
Evaluating eval...:  11%|█         | 208/1900 [04:13<33:57,  1.20s/it]
+
+
Evaluating eval...:  11%|█         | 209/1900 [04:15<33:38,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 210/1900 [04:16<33:24,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 211/1900 [04:17<33:29,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 212/1900 [04:18<33:25,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 213/1900 [04:19<34:12,  1.22s/it]
+
+
Evaluating eval...:  11%|█▏        | 214/1900 [04:21<34:44,  1.24s/it]
+
+
Evaluating eval...:  11%|█▏        | 215/1900 [04:22<34:24,  1.23s/it]
+
+
Evaluating eval...:  11%|█▏        | 216/1900 [04:23<34:00,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 217/1900 [04:24<34:00,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 218/1900 [04:26<34:41,  1.24s/it]
+
+
Evaluating eval...:  12%|█▏        | 219/1900 [04:27<34:30,  1.23s/it]
+
+
Evaluating eval...:  12%|█▏        | 220/1900 [04:28<34:31,  1.23s/it]
+
+
Evaluating eval...:  12%|█▏        | 221/1900 [04:29<34:19,  1.23s/it]
+
+
Evaluating eval...:  12%|█▏        | 222/1900 [04:30<33:51,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 223/1900 [04:32<33:21,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 224/1900 [04:33<33:04,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 225/1900 [04:34<32:55,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 226/1900 [04:35<33:04,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 227/1900 [04:36<32:59,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 228/1900 [04:38<33:27,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 229/1900 [04:39<32:53,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 230/1900 [04:40<32:59,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 231/1900 [04:41<33:10,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 232/1900 [04:42<32:47,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 233/1900 [04:44<33:20,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 234/1900 [04:45<33:07,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 235/1900 [04:46<33:02,  1.19s/it]
+
+
Evaluating eval...:  12%|█▏        | 236/1900 [04:47<33:31,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 237/1900 [04:48<33:58,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 238/1900 [04:50<33:55,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 239/1900 [04:51<34:33,  1.25s/it]
+
+
Evaluating eval...:  13%|█▎        | 240/1900 [04:52<33:53,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 241/1900 [04:53<33:35,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 242/1900 [04:55<33:29,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 243/1900 [04:56<32:58,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 244/1900 [04:57<32:55,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 245/1900 [04:58<33:41,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 246/1900 [04:59<33:31,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 247/1900 [05:01<33:14,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 248/1900 [05:02<33:08,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 249/1900 [05:03<33:00,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 250/1900 [05:04<33:08,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 251/1900 [05:05<33:24,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 252/1900 [05:07<32:59,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 253/1900 [05:08<33:21,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 254/1900 [05:09<33:07,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 255/1900 [05:10<32:54,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 256/1900 [05:11<32:43,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 257/1900 [05:12<32:26,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 258/1900 [05:14<32:01,  1.17s/it]
+
+
Evaluating eval...:  14%|█▎        | 259/1900 [05:15<32:29,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 260/1900 [05:16<32:34,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 261/1900 [05:17<32:29,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 262/1900 [05:18<32:08,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 263/1900 [05:20<32:19,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 264/1900 [05:21<32:21,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 265/1900 [05:22<32:39,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 266/1900 [05:23<32:49,  1.21s/it]
+
+
Evaluating eval...:  14%|█▍        | 267/1900 [05:25<33:18,  1.22s/it]
+
+
Evaluating eval...:  14%|█▍        | 268/1900 [05:26<32:55,  1.21s/it]
+
+
Evaluating eval...:  14%|█▍        | 269/1900 [05:27<32:26,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 270/1900 [05:28<32:13,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 271/1900 [05:29<31:48,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 272/1900 [05:30<32:36,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 273/1900 [05:32<32:40,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 274/1900 [05:33<32:37,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 275/1900 [05:34<32:38,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 276/1900 [05:35<33:16,  1.23s/it]
+
+
Evaluating eval...:  15%|█▍        | 277/1900 [05:36<32:41,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 278/1900 [05:38<32:32,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 279/1900 [05:39<33:04,  1.22s/it]
+
+
Evaluating eval...:  15%|█▍        | 280/1900 [05:40<32:57,  1.22s/it]
+
+
Evaluating eval...:  15%|█▍        | 281/1900 [05:41<32:53,  1.22s/it]
+
+
Evaluating eval...:  15%|█▍        | 282/1900 [05:43<32:45,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 283/1900 [05:44<32:42,  1.21s/it]
+
+
Evaluating eval...:  15%|█▍        | 284/1900 [05:45<32:35,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 285/1900 [05:46<32:16,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 286/1900 [05:47<32:29,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 287/1900 [05:49<32:27,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 288/1900 [05:51<41:46,  1.55s/it]
+
+
Evaluating eval...:  15%|█▌        | 289/1900 [05:52<39:08,  1.46s/it]
+
+
Evaluating eval...:  15%|█▌        | 290/1900 [05:53<36:38,  1.37s/it]
+
+
Evaluating eval...:  15%|█▌        | 291/1900 [05:55<35:15,  1.31s/it]
+
+
Evaluating eval...:  15%|█▌        | 292/1900 [05:56<34:28,  1.29s/it]
+
+
Evaluating eval...:  15%|█▌        | 293/1900 [05:57<33:36,  1.25s/it]
+
+
Evaluating eval...:  15%|█▌        | 294/1900 [05:58<33:05,  1.24s/it]
+
+
Evaluating eval...:  16%|█▌        | 295/1900 [05:59<32:46,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 296/1900 [06:01<32:54,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 297/1900 [06:02<32:59,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 298/1900 [06:03<33:17,  1.25s/it]
+
+
Evaluating eval...:  16%|█▌        | 299/1900 [06:04<32:35,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 300/1900 [06:05<32:28,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 301/1900 [06:07<32:51,  1.23s/it]
+
+
Evaluating eval...:  16%|█▌        | 302/1900 [06:08<32:17,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 303/1900 [06:09<31:52,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 304/1900 [06:10<31:32,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 305/1900 [06:11<31:34,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 306/1900 [06:13<31:57,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 307/1900 [06:14<31:49,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 308/1900 [06:15<31:42,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 309/1900 [06:16<31:33,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 310/1900 [06:17<31:50,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 311/1900 [06:19<32:23,  1.22s/it]
+
+
Evaluating eval...:  16%|█▋        | 312/1900 [06:20<32:06,  1.21s/it]
+
+
Evaluating eval...:  16%|█▋        | 313/1900 [06:21<31:46,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 314/1900 [06:22<31:44,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 315/1900 [06:23<31:48,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 316/1900 [06:25<31:38,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 317/1900 [06:26<32:00,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 318/1900 [06:27<32:12,  1.22s/it]
+
+
Evaluating eval...:  17%|█▋        | 319/1900 [06:28<32:22,  1.23s/it]
+
+
Evaluating eval...:  17%|█▋        | 320/1900 [06:30<32:13,  1.22s/it]
+
+
Evaluating eval...:  17%|█▋        | 321/1900 [06:31<31:38,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 322/1900 [06:32<31:42,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 323/1900 [06:33<31:41,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 324/1900 [06:34<31:05,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 325/1900 [06:36<31:07,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 326/1900 [06:37<31:05,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 327/1900 [06:38<31:07,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 328/1900 [06:39<31:52,  1.22s/it]
+
+
Evaluating eval...:  17%|█▋        | 329/1900 [06:40<31:21,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 330/1900 [06:42<31:43,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 331/1900 [06:43<32:41,  1.25s/it]
+
+
Evaluating eval...:  17%|█▋        | 332/1900 [06:44<32:32,  1.25s/it]
+
+
Evaluating eval...:  18%|█▊        | 333/1900 [06:45<32:19,  1.24s/it]
+
+
Evaluating eval...:  18%|█▊        | 334/1900 [06:47<31:28,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 335/1900 [06:48<30:59,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 336/1900 [06:49<31:06,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 337/1900 [06:50<30:58,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 338/1900 [06:51<31:40,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 339/1900 [06:53<31:45,  1.22s/it]
+
+
Evaluating eval...:  18%|█▊        | 340/1900 [06:54<31:21,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 341/1900 [06:55<31:20,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 342/1900 [06:56<31:05,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 343/1900 [06:57<31:01,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 344/1900 [06:58<31:02,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 345/1900 [07:00<30:53,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 346/1900 [07:01<30:33,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 347/1900 [07:02<30:35,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 348/1900 [07:03<30:17,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 349/1900 [07:04<30:07,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 350/1900 [07:05<30:04,  1.16s/it]
+
+
Evaluating eval...:  18%|█▊        | 351/1900 [07:07<30:30,  1.18s/it]
+
+
Evaluating eval...:  19%|█▊        | 352/1900 [07:08<30:29,  1.18s/it]
+
+
Evaluating eval...:  19%|█▊        | 353/1900 [07:09<30:56,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 354/1900 [07:10<31:08,  1.21s/it]
+
+
Evaluating eval...:  19%|█▊        | 355/1900 [07:12<31:48,  1.24s/it]
+
+
Evaluating eval...:  19%|█▊        | 356/1900 [07:13<32:02,  1.24s/it]
+
+
Evaluating eval...:  19%|█▉        | 357/1900 [07:14<31:29,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 358/1900 [07:15<31:41,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 359/1900 [07:17<31:21,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 360/1900 [07:18<31:05,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 361/1900 [07:19<30:45,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 362/1900 [07:20<31:38,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 363/1900 [07:21<30:55,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 364/1900 [07:23<30:32,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 365/1900 [07:24<30:24,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 366/1900 [07:25<29:59,  1.17s/it]
+
+
Evaluating eval...:  19%|█▉        | 367/1900 [07:27<37:14,  1.46s/it]
+
+
Evaluating eval...:  19%|█▉        | 368/1900 [07:28<35:48,  1.40s/it]
+
+
Evaluating eval...:  19%|█▉        | 369/1900 [07:29<34:22,  1.35s/it]
+
+
Evaluating eval...:  19%|█▉        | 370/1900 [07:31<33:14,  1.30s/it]
+
+
Evaluating eval...:  20%|█▉        | 371/1900 [07:32<32:13,  1.26s/it]
+
+
Evaluating eval...:  20%|█▉        | 372/1900 [07:33<31:35,  1.24s/it]
+
+
Evaluating eval...:  20%|█▉        | 373/1900 [07:34<31:00,  1.22s/it]
+
+
Evaluating eval...:  20%|█▉        | 374/1900 [07:35<30:27,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 375/1900 [07:36<30:08,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 376/1900 [07:38<30:36,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 377/1900 [07:39<31:14,  1.23s/it]
+
+
Evaluating eval...:  20%|█▉        | 378/1900 [07:40<31:17,  1.23s/it]
+
+
Evaluating eval...:  20%|█▉        | 379/1900 [07:41<30:48,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 380/1900 [07:43<30:52,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 381/1900 [07:44<31:09,  1.23s/it]
+
+
Evaluating eval...:  20%|██        | 382/1900 [07:45<31:12,  1.23s/it]
+
+
Evaluating eval...:  20%|██        | 383/1900 [07:46<30:45,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 384/1900 [07:47<30:22,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 385/1900 [07:49<30:05,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 386/1900 [07:50<30:12,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 387/1900 [07:51<30:35,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 388/1900 [07:52<30:36,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 389/1900 [07:54<30:40,  1.22s/it]
+
+
Evaluating eval...:  21%|██        | 390/1900 [07:55<30:38,  1.22s/it]
+
+
Evaluating eval...:  21%|██        | 391/1900 [07:56<30:35,  1.22s/it]
+
+
Evaluating eval...:  21%|██        | 392/1900 [07:57<30:04,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 393/1900 [07:58<29:54,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 394/1900 [08:00<30:05,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 395/1900 [08:01<29:43,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 396/1900 [08:02<30:06,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 397/1900 [08:03<30:09,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 398/1900 [08:04<29:47,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 399/1900 [08:06<30:09,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 400/1900 [08:07<30:05,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 401/1900 [08:08<30:18,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 402/1900 [08:09<29:54,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 403/1900 [08:10<30:13,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 404/1900 [08:12<30:29,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 405/1900 [08:13<30:19,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 406/1900 [08:14<30:02,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 407/1900 [08:15<30:00,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 408/1900 [08:17<30:40,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 409/1900 [08:18<30:44,  1.24s/it]
+
+
Evaluating eval...:  22%|██▏       | 410/1900 [08:19<30:44,  1.24s/it]
+
+
Evaluating eval...:  22%|██▏       | 411/1900 [08:20<30:42,  1.24s/it]
+
+
Evaluating eval...:  22%|██▏       | 412/1900 [08:21<30:09,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 413/1900 [08:23<30:31,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 414/1900 [08:24<30:10,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 415/1900 [08:25<29:31,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 416/1900 [08:26<29:12,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 417/1900 [08:27<29:41,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 418/1900 [08:29<29:24,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 419/1900 [08:30<29:07,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 420/1900 [08:31<29:27,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 421/1900 [08:32<29:55,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 422/1900 [08:33<29:41,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 423/1900 [08:35<30:22,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 424/1900 [08:36<30:15,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 425/1900 [08:37<30:02,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 426/1900 [08:38<30:14,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 427/1900 [08:40<30:02,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 428/1900 [08:41<29:36,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 429/1900 [08:42<29:53,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 430/1900 [08:43<29:27,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 431/1900 [08:44<29:29,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 432/1900 [08:46<29:58,  1.23s/it]
+
+
Evaluating eval...:  23%|██▎       | 433/1900 [08:47<29:42,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 434/1900 [08:48<30:14,  1.24s/it]
+
+
Evaluating eval...:  23%|██▎       | 435/1900 [08:49<29:43,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 436/1900 [08:51<29:59,  1.23s/it]
+
+
Evaluating eval...:  23%|██▎       | 437/1900 [08:52<29:23,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 438/1900 [08:53<29:13,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 439/1900 [08:54<29:36,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 440/1900 [08:55<29:20,  1.21s/it]
+
+
Evaluating eval...:  23%|██▎       | 441/1900 [08:57<29:15,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 442/1900 [08:58<28:42,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 443/1900 [08:59<28:50,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 444/1900 [09:00<28:46,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 445/1900 [09:01<29:09,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 446/1900 [09:03<29:25,  1.21s/it]
+
+
Evaluating eval...:  24%|██▎       | 447/1900 [09:04<28:58,  1.20s/it]
+
+
Evaluating eval...:  24%|██▎       | 448/1900 [09:05<28:55,  1.20s/it]
+
+
Evaluating eval...:  24%|██▎       | 449/1900 [09:06<29:05,  1.20s/it]
+
+
Evaluating eval...:  24%|██▎       | 450/1900 [09:07<28:59,  1.20s/it]
+
+
Evaluating eval...:  24%|██▎       | 451/1900 [09:08<29:00,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 452/1900 [09:10<28:39,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 453/1900 [09:11<29:28,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 454/1900 [09:12<29:37,  1.23s/it]
+
+
Evaluating eval...:  24%|██▍       | 455/1900 [09:13<29:22,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 456/1900 [09:15<29:40,  1.23s/it]
+
+
Evaluating eval...:  24%|██▍       | 457/1900 [09:16<29:22,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 458/1900 [09:17<29:16,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 459/1900 [09:18<28:39,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 460/1900 [09:19<28:22,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 461/1900 [09:21<28:55,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 462/1900 [09:22<29:08,  1.22s/it]
+
+
Evaluating eval...:  24%|██▍       | 463/1900 [09:23<28:59,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 464/1900 [09:24<29:01,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 465/1900 [09:25<28:49,  1.21s/it]
+
+
Evaluating eval...:  25%|██▍       | 466/1900 [09:27<28:20,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 467/1900 [09:28<28:20,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 468/1900 [09:29<28:37,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 469/1900 [09:30<28:40,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 470/1900 [09:31<28:43,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 471/1900 [09:33<28:29,  1.20s/it]
+
+
Evaluating eval...:  25%|██▍       | 472/1900 [09:34<29:17,  1.23s/it]
+
+
Evaluating eval...:  25%|██▍       | 473/1900 [09:35<28:52,  1.21s/it]
+
+
Evaluating eval...:  25%|██▍       | 474/1900 [09:36<28:38,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 475/1900 [09:38<28:46,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 476/1900 [09:39<28:26,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 477/1900 [09:40<29:31,  1.25s/it]
+
+
Evaluating eval...:  25%|██▌       | 478/1900 [09:41<29:18,  1.24s/it]
+
+
Evaluating eval...:  25%|██▌       | 479/1900 [09:43<29:32,  1.25s/it]
+
+
Evaluating eval...:  25%|██▌       | 480/1900 [09:44<29:01,  1.23s/it]
+
+
Evaluating eval...:  25%|██▌       | 481/1900 [09:45<30:03,  1.27s/it]
+
+
Evaluating eval...:  25%|██▌       | 482/1900 [09:46<29:14,  1.24s/it]
+
+
Evaluating eval...:  25%|██▌       | 483/1900 [09:47<28:54,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 484/1900 [09:49<29:20,  1.24s/it]
+
+
Evaluating eval...:  26%|██▌       | 485/1900 [09:50<28:41,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 486/1900 [09:51<28:07,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 487/1900 [09:52<28:08,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 488/1900 [09:53<28:26,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 489/1900 [09:55<28:14,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 490/1900 [09:56<28:04,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 491/1900 [09:57<28:34,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 492/1900 [09:58<28:19,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 493/1900 [10:00<29:23,  1.25s/it]
+
+
Evaluating eval...:  26%|██▌       | 494/1900 [10:01<28:47,  1.23s/it]
+
+
Evaluating eval...:  26%|██▌       | 495/1900 [10:02<28:22,  1.21s/it]
+
+
Evaluating eval...:  26%|██▌       | 496/1900 [10:03<28:50,  1.23s/it]
+
+
Evaluating eval...:  26%|██▌       | 497/1900 [10:05<29:10,  1.25s/it]
+
+
Evaluating eval...:  26%|██▌       | 498/1900 [10:06<29:21,  1.26s/it]
+
+
Evaluating eval...:  26%|██▋       | 499/1900 [10:07<29:07,  1.25s/it]
+
+
Evaluating eval...:  26%|██▋       | 500/1900 [10:08<28:54,  1.24s/it]
+
+
Evaluating eval...:  26%|██▋       | 501/1900 [10:10<29:13,  1.25s/it]
+
+
Evaluating eval...:  26%|██▋       | 502/1900 [10:11<28:50,  1.24s/it]
+
+
Evaluating eval...:  26%|██▋       | 503/1900 [10:12<29:04,  1.25s/it]
+
+
Evaluating eval...:  27%|██▋       | 504/1900 [10:13<28:58,  1.25s/it]
+
+
Evaluating eval...:  27%|██▋       | 505/1900 [10:14<28:44,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 506/1900 [10:16<28:39,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 507/1900 [10:17<28:03,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 508/1900 [10:18<28:42,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 509/1900 [10:19<29:20,  1.27s/it]
+
+
Evaluating eval...:  27%|██▋       | 510/1900 [10:21<28:56,  1.25s/it]
+
+
Evaluating eval...:  27%|██▋       | 511/1900 [10:22<28:26,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 512/1900 [10:23<28:12,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 513/1900 [10:24<27:44,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 514/1900 [10:25<27:28,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 515/1900 [10:27<28:13,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 516/1900 [10:28<27:54,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 517/1900 [10:29<27:46,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 518/1900 [10:30<28:09,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 519/1900 [10:32<28:31,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 520/1900 [10:33<27:59,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 521/1900 [10:34<28:10,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 522/1900 [10:35<27:43,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 523/1900 [10:36<27:45,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 524/1900 [10:38<27:51,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 525/1900 [10:39<27:26,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 526/1900 [10:40<27:25,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 527/1900 [10:41<27:43,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 528/1900 [10:42<27:36,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 529/1900 [10:44<28:11,  1.23s/it]
+
+
Evaluating eval...:  28%|██▊       | 530/1900 [10:45<27:49,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 531/1900 [10:46<27:33,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 532/1900 [10:47<28:14,  1.24s/it]
+
+
Evaluating eval...:  28%|██▊       | 533/1900 [10:49<27:43,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 534/1900 [10:50<27:43,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 535/1900 [10:51<27:18,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 536/1900 [10:52<27:15,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 537/1900 [10:53<27:24,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 538/1900 [10:55<27:23,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 539/1900 [10:56<27:18,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 540/1900 [10:57<27:25,  1.21s/it]
+
+
Evaluating eval...:  28%|█��▊       | 541/1900 [10:58<27:01,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 542/1900 [10:59<27:20,  1.21s/it]
+
+
Evaluating eval...:  29%|██▊       | 543/1900 [11:01<26:53,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 544/1900 [11:02<26:44,  1.18s/it]
+
+
Evaluating eval...:  29%|██▊       | 545/1900 [11:03<27:55,  1.24s/it]
+
+
Evaluating eval...:  29%|██▊       | 546/1900 [11:04<27:41,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 547/1900 [11:06<27:59,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 548/1900 [11:07<27:50,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 549/1900 [11:08<28:11,  1.25s/it]
+
+
Evaluating eval...:  29%|██▉       | 550/1900 [11:09<28:27,  1.26s/it]
+
+
Evaluating eval...:  29%|██▉       | 551/1900 [11:11<27:45,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 552/1900 [11:12<28:14,  1.26s/it]
+
+
Evaluating eval...:  29%|██▉       | 553/1900 [11:13<27:58,  1.25s/it]
+
+
Evaluating eval...:  29%|██▉       | 554/1900 [11:14<27:26,  1.22s/it]
+
+
Evaluating eval...:  29%|██▉       | 555/1900 [11:15<27:10,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 556/1900 [11:17<27:05,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 557/1900 [11:18<26:40,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 558/1900 [11:19<26:46,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 559/1900 [11:20<26:34,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 560/1900 [11:21<26:49,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 561/1900 [11:23<26:33,  1.19s/it]
+
+
Evaluating eval...:  30%|██▉       | 562/1900 [11:24<26:33,  1.19s/it]
+
+
Evaluating eval...:  30%|██▉       | 563/1900 [11:25<27:09,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 564/1900 [11:26<27:29,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 565/1900 [11:27<27:21,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 566/1900 [11:29<28:04,  1.26s/it]
+
+
Evaluating eval...:  30%|██▉       | 567/1900 [11:30<27:59,  1.26s/it]
+
+
Evaluating eval...:  30%|██▉       | 568/1900 [11:31<28:01,  1.26s/it]
+
+
Evaluating eval...:  30%|██▉       | 569/1900 [11:33<27:33,  1.24s/it]
+
+
Evaluating eval...:  30%|███       | 570/1900 [11:35<35:08,  1.59s/it]
+
+
Evaluating eval...:  30%|███       | 571/1900 [11:36<32:20,  1.46s/it]
+
+
Evaluating eval...:  30%|███       | 572/1900 [11:37<30:30,  1.38s/it]
+
+
Evaluating eval...:  30%|███       | 573/1900 [11:38<29:21,  1.33s/it]
+
+
Evaluating eval...:  30%|███       | 574/1900 [11:40<28:28,  1.29s/it]
+
+
Evaluating eval...:  30%|███       | 575/1900 [11:41<27:37,  1.25s/it]
+
+
Evaluating eval...:  30%|███       | 576/1900 [11:42<27:17,  1.24s/it]
+
+
Evaluating eval...:  30%|███       | 577/1900 [11:43<27:15,  1.24s/it]
+
+
Evaluating eval...:  30%|███       | 578/1900 [11:45<27:04,  1.23s/it]
+
+
Evaluating eval...:  30%|███       | 579/1900 [11:46<27:15,  1.24s/it]
+
+
Evaluating eval...:  31%|███       | 580/1900 [11:47<26:51,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 581/1900 [11:48<26:38,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 582/1900 [11:49<27:30,  1.25s/it]
+
+
Evaluating eval...:  31%|███       | 583/1900 [11:51<26:59,  1.23s/it]
+
+
Evaluating eval...:  31%|███       | 584/1900 [11:52<26:36,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 585/1900 [11:53<26:12,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 586/1900 [11:54<26:31,  1.21s/it]
+
+
Evaluating eval...:  31%|███       | 587/1900 [11:55<26:15,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 588/1900 [11:57<26:03,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 589/1900 [11:58<26:03,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 590/1900 [11:59<26:12,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 591/1900 [12:00<26:07,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 592/1900 [12:01<26:35,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 593/1900 [12:03<26:28,  1.22s/it]
+
+
Evaluating eval...:  31%|███▏      | 594/1900 [12:04<26:26,  1.21s/it]
+
+
Evaluating eval...:  31%|███▏      | 595/1900 [12:05<26:12,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 596/1900 [12:06<26:22,  1.21s/it]
+
+
Evaluating eval...:  31%|███▏      | 597/1900 [12:08<26:40,  1.23s/it]
+
+
Evaluating eval...:  31%|███▏      | 598/1900 [12:09<26:18,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 599/1900 [12:10<26:14,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 600/1900 [12:11<26:02,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 601/1900 [12:12<26:04,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 602/1900 [12:13<25:42,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 603/1900 [12:15<25:41,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 604/1900 [12:16<25:45,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 605/1900 [12:17<25:59,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 606/1900 [12:18<26:22,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 607/1900 [12:20<25:53,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 608/1900 [12:21<26:12,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 609/1900 [12:22<26:28,  1.23s/it]
+
+
Evaluating eval...:  32%|███▏      | 610/1900 [12:23<25:56,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 611/1900 [12:24<25:45,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 612/1900 [12:26<26:08,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 613/1900 [12:27<26:00,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 614/1900 [12:28<26:26,  1.23s/it]
+
+
Evaluating eval...:  32%|███▏      | 615/1900 [12:29<26:07,  1.22s/it]
+
+
Evaluating eval...:  32%|███▏      | 616/1900 [12:30<25:50,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 617/1900 [12:32<25:25,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 618/1900 [12:33<25:14,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 619/1900 [12:34<25:40,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 620/1900 [12:35<25:28,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 621/1900 [12:36<25:36,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 622/1900 [12:38<25:34,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 623/1900 [12:39<25:49,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 624/1900 [12:40<26:10,  1.23s/it]
+
+
Evaluating eval...:  33%|███▎      | 625/1900 [12:41<26:46,  1.26s/it]
+
+
Evaluating eval...:  33%|███▎      | 626/1900 [12:43<26:18,  1.24s/it]
+
+
Evaluating eval...:  33%|███▎      | 627/1900 [12:44<26:00,  1.23s/it]
+
+
Evaluating eval...:  33%|███▎      | 628/1900 [12:45<26:03,  1.23s/it]
+
+
Evaluating eval...:  33%|███▎      | 629/1900 [12:46<26:11,  1.24s/it]
+
+
Evaluating eval...:  33%|███▎      | 630/1900 [12:48<26:03,  1.23s/it]
+
+
Evaluating eval...:  33%|███▎      | 631/1900 [12:49<26:22,  1.25s/it]
+
+
Evaluating eval...:  33%|███▎      | 632/1900 [12:50<25:54,  1.23s/it]
+
+
Evaluating eval...:  33%|███▎      | 633/1900 [12:51<25:29,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 634/1900 [12:52<25:04,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 635/1900 [12:54<25:02,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 636/1900 [12:55<25:19,  1.20s/it]
+
+
Evaluating eval...:  34%|███▎      | 637/1900 [12:56<25:36,  1.22s/it]
+
+
Evaluating eval...:  34%|███▎      | 638/1900 [12:57<25:58,  1.23s/it]
+
+
Evaluating eval...:  34%|███▎      | 639/1900 [12:59<26:05,  1.24s/it]
+
+
Evaluating eval...:  34%|███▎      | 640/1900 [13:00<26:06,  1.24s/it]
+
+
Evaluating eval...:  34%|███▎      | 641/1900 [13:01<26:01,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 642/1900 [13:02<25:41,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 643/1900 [13:04<26:06,  1.25s/it]
+
+
Evaluating eval...:  34%|███▍      | 644/1900 [13:05<25:46,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 645/1900 [13:06<25:40,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 646/1900 [13:07<25:59,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 647/1900 [13:08<25:39,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 648/1900 [13:10<25:24,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 649/1900 [13:11<25:48,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 650/1900 [13:12<25:57,  1.25s/it]
+
+
Evaluating eval...:  34%|███▍      | 651/1900 [13:13<25:49,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 652/1900 [13:15<25:18,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 653/1900 [13:16<24:57,  1.20s/it]
+
+
Evaluating eval...:  34%|███▍      | 654/1900 [13:17<25:14,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 655/1900 [13:18<25:43,  1.24s/it]
+
+
Evaluating eval...:  35%|███▍      | 656/1900 [13:19<25:32,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 657/1900 [13:21<25:13,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 658/1900 [13:22<25:49,  1.25s/it]
+
+
Evaluating eval...:  35%|███▍      | 659/1900 [13:23<25:44,  1.24s/it]
+
+
Evaluating eval...:  35%|███▍      | 660/1900 [13:24<25:21,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 661/1900 [13:26<25:04,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 662/1900 [13:27<25:25,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 663/1900 [13:28<25:35,  1.24s/it]
+
+
Evaluating eval...:  35%|███▍      | 664/1900 [13:29<25:26,  1.23s/it]
+
+
Evaluating eval...:  35%|███▌      | 665/1900 [13:31<25:07,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 666/1900 [13:32<24:50,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 667/1900 [13:33<25:46,  1.25s/it]
+
+
Evaluating eval...:  35%|███▌      | 668/1900 [13:34<25:18,  1.23s/it]
+
+
Evaluating eval...:  35%|███▌      | 669/1900 [13:35<24:52,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 670/1900 [13:37<24:48,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 671/1900 [13:38<25:03,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 672/1900 [13:39<24:53,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 673/1900 [13:40<25:16,  1.24s/it]
+
+
Evaluating eval...:  35%|███▌      | 674/1900 [13:42<25:12,  1.23s/it]
+
+
Evaluating eval...:  36%|███▌      | 675/1900 [13:43<25:13,  1.24s/it]
+
+
Evaluating eval...:  36%|███▌      | 676/1900 [13:44<24:51,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 677/1900 [13:45<24:48,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 678/1900 [13:47<25:25,  1.25s/it]
+
+
Evaluating eval...:  36%|███▌      | 679/1900 [13:48<25:03,  1.23s/it]
+
+
Evaluating eval...:  36%|███▌      | 680/1900 [13:49<25:11,  1.24s/it]
+
+
Evaluating eval...:  36%|███▌      | 681/1900 [13:50<25:56,  1.28s/it]
+
+
Evaluating eval...:  36%|███▌      | 682/1900 [13:52<25:36,  1.26s/it]
+
+
Evaluating eval...:  36%|███▌      | 683/1900 [13:53<25:33,  1.26s/it]
+
+
Evaluating eval...:  36%|███▌      | 684/1900 [13:54<25:05,  1.24s/it]
+
+
Evaluating eval...:  36%|███▌      | 685/1900 [13:55<24:43,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 686/1900 [13:56<25:04,  1.24s/it]
+
+
Evaluating eval...:  36%|███▌      | 687/1900 [13:58<24:50,  1.23s/it]
+
+
Evaluating eval...:  36%|███▌      | 688/1900 [13:59<24:21,  1.21s/it]
+
+
Evaluating eval...:  36%|███▋      | 689/1900 [14:00<24:09,  1.20s/it]
+
+
Evaluating eval...:  36%|███▋      | 690/1900 [14:01<24:14,  1.20s/it]
+
+
Evaluating eval...:  36%|███▋      | 691/1900 [14:02<24:16,  1.20s/it]
+
+
Evaluating eval...:  36%|███▋      | 692/1900 [14:04<23:55,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 693/1900 [14:05<23:55,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 694/1900 [14:06<23:58,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 695/1900 [14:07<24:19,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 696/1900 [14:08<24:42,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 697/1900 [14:10<24:20,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 698/1900 [14:11<24:35,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 699/1900 [14:12<24:49,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 700/1900 [14:13<24:24,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 701/1900 [14:15<24:34,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 702/1900 [14:16<24:29,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 703/1900 [14:17<23:59,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 704/1900 [14:18<24:48,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 705/1900 [14:20<24:22,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 706/1900 [14:21<24:02,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 707/1900 [14:22<23:54,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 708/1900 [14:23<24:12,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 709/1900 [14:24<23:53,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 710/1900 [14:26<23:52,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 711/1900 [14:27<24:26,  1.23s/it]
+
+
Evaluating eval...:  37%|███▋      | 712/1900 [14:28<24:25,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 713/1900 [14:29<25:11,  1.27s/it]
+
+
Evaluating eval...:  38%|███▊      | 714/1900 [14:31<24:38,  1.25s/it]
+
+
Evaluating eval...:  38%|███▊      | 715/1900 [14:32<24:07,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 716/1900 [14:33<23:53,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 717/1900 [14:34<23:41,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 718/1900 [14:35<23:57,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 719/1900 [14:37<23:48,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 720/1900 [14:38<23:39,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 721/1900 [14:39<23:48,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 722/1900 [14:40<23:34,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 723/1900 [14:41<23:33,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 724/1900 [14:43<23:22,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 725/1900 [14:44<23:12,  1.18s/it]
+
+
Evaluating eval...:  38%|███▊      | 726/1900 [14:45<23:49,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 727/1900 [14:46<23:29,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 728/1900 [14:47<24:05,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 729/1900 [14:49<23:44,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 730/1900 [14:50<24:00,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 731/1900 [14:51<23:45,  1.22s/it]
+
+
Evaluating eval...:  39%|███▊      | 732/1900 [14:52<23:37,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 733/1900 [14:54<23:33,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 734/1900 [14:55<23:24,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 735/1900 [14:56<23:09,  1.19s/it]
+
+
Evaluating eval...:  39%|███▊      | 736/1900 [14:57<23:06,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 737/1900 [14:58<22:56,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 738/1900 [14:59<22:58,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 739/1900 [15:01<22:48,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 740/1900 [15:02<22:44,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 741/1900 [15:03<23:49,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 742/1900 [15:04<23:28,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 743/1900 [15:06<23:48,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 744/1900 [15:07<23:30,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 745/1900 [15:08<23:39,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 746/1900 [15:09<23:22,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 747/1900 [15:10<23:51,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 748/1900 [15:12<23:35,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 749/1900 [15:13<24:02,  1.25s/it]
+
+
Evaluating eval...:  39%|███▉      | 750/1900 [15:14<23:31,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 751/1900 [15:15<23:28,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 752/1900 [15:17<23:33,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 753/1900 [15:18<23:19,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 754/1900 [15:19<22:54,  1.20s/it]
+
+
Evaluating eval...:  40%|███▉      | 755/1900 [15:20<22:35,  1.18s/it]
+
+
Evaluating eval...:  40%|███▉      | 756/1900 [15:21<23:14,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 757/1900 [15:23<23:02,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 758/1900 [15:24<23:22,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 759/1900 [15:25<23:20,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 760/1900 [15:26<23:27,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 761/1900 [15:28<23:02,  1.21s/it]
+
+
Evaluating eval...:  40%|████      | 762/1900 [15:29<22:39,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 763/1900 [15:30<22:35,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 764/1900 [15:31<22:26,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 765/1900 [15:32<22:34,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 766/1900 [15:33<22:41,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 767/1900 [15:35<22:58,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 768/1900 [15:36<23:43,  1.26s/it]
+
+
Evaluating eval...:  40%|████      | 769/1900 [15:37<23:40,  1.26s/it]
+
+
Evaluating eval...:  41%|████      | 770/1900 [15:38<23:09,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 771/1900 [15:40<22:54,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 772/1900 [15:41<22:53,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 773/1900 [15:42<22:38,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 774/1900 [15:43<22:15,  1.19s/it]
+
+
Evaluating eval...:  41%|████      | 775/1900 [15:44<22:33,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 776/1900 [15:46<22:39,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 777/1900 [15:47<23:10,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 778/1900 [15:48<22:49,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 779/1900 [15:49<22:40,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 780/1900 [15:51<23:29,  1.26s/it]
+
+
Evaluating eval...:  41%|████      | 781/1900 [15:52<23:07,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 782/1900 [15:53<23:34,  1.27s/it]
+
+
Evaluating eval...:  41%|████      | 783/1900 [15:54<23:17,  1.25s/it]
+
+
Evaluating eval...:  41%|████▏     | 784/1900 [15:56<22:52,  1.23s/it]
+
+
Evaluating eval...:  41%|████▏     | 785/1900 [15:57<22:37,  1.22s/it]
+
+
Evaluating eval...:  41%|████▏     | 786/1900 [15:58<22:26,  1.21s/it]
+
+
Evaluating eval...:  41%|████▏     | 787/1900 [15:59<22:28,  1.21s/it]
+
+
Evaluating eval...:  41%|████▏     | 788/1900 [16:00<22:23,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 789/1900 [16:02<22:34,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 790/1900 [16:03<22:46,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 791/1900 [16:04<22:50,  1.24s/it]
+
+
Evaluating eval...:  42%|████▏     | 792/1900 [16:05<23:06,  1.25s/it]
+
+
Evaluating eval...:  42%|████▏     | 793/1900 [16:07<22:52,  1.24s/it]
+
+
Evaluating eval...:  42%|████▏     | 794/1900 [16:08<22:28,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 795/1900 [16:09<22:29,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 796/1900 [16:10<22:07,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 797/1900 [16:11<21:56,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 798/1900 [16:13<21:53,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 799/1900 [16:14<21:46,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 800/1900 [16:15<22:22,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 801/1900 [16:16<22:20,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 802/1900 [16:17<21:53,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 803/1900 [16:19<22:25,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 804/1900 [16:20<22:08,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 805/1900 [16:21<22:27,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 806/1900 [16:22<21:57,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 807/1900 [16:24<21:51,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 808/1900 [16:25<22:37,  1.24s/it]
+
+
Evaluating eval...:  43%|████▎     | 809/1900 [16:26<22:50,  1.26s/it]
+
+
Evaluating eval...:  43%|████▎     | 810/1900 [16:27<22:26,  1.24s/it]
+
+
Evaluating eval...:  43%|████▎     | 811/1900 [16:29<22:06,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 812/1900 [16:30<22:17,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 813/1900 [16:31<21:52,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 814/1900 [16:32<21:42,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 815/1900 [16:33<21:45,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 816/1900 [16:35<21:43,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 817/1900 [16:36<21:34,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 818/1900 [16:37<21:59,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 819/1900 [16:38<21:52,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 820/1900 [16:39<21:43,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 821/1900 [16:41<21:36,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 822/1900 [16:42<21:37,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 823/1900 [16:43<21:33,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 824/1900 [16:44<21:29,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 825/1900 [16:45<21:20,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 826/1900 [16:47<21:59,  1.23s/it]
+
+
Evaluating eval...:  44%|████▎     | 827/1900 [16:48<21:55,  1.23s/it]
+
+
Evaluating eval...:  44%|████▎     | 828/1900 [16:49<21:46,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 829/1900 [16:50<21:20,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 830/1900 [16:51<21:25,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 831/1900 [16:53<21:08,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 832/1900 [16:54<21:23,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 833/1900 [16:55<21:19,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 834/1900 [16:56<21:00,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 835/1900 [16:57<21:36,  1.22s/it]
+
+
Evaluating eval...:  44%|████▍     | 836/1900 [16:59<21:35,  1.22s/it]
+
+
Evaluating eval...:  44%|████▍     | 837/1900 [17:00<21:25,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 838/1900 [17:01<21:00,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 839/1900 [17:02<20:47,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 840/1900 [17:03<20:46,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 841/1900 [17:05<21:05,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 842/1900 [17:06<21:03,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 843/1900 [17:07<20:51,  1.18s/it]
+
+
Evaluating eval...:  44%|████▍     | 844/1900 [17:08<20:35,  1.17s/it]
+
+
Evaluating eval...:  44%|████▍     | 845/1900 [17:09<20:36,  1.17s/it]
+
+
Evaluating eval...:  45%|████▍     | 846/1900 [17:10<21:01,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 847/1900 [17:12<20:46,  1.18s/it]
+
+
Evaluating eval...:  45%|████▍     | 848/1900 [17:13<21:03,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 849/1900 [17:14<20:50,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 850/1900 [17:15<21:00,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 851/1900 [17:16<20:55,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 852/1900 [17:18<21:14,  1.22s/it]
+
+
Evaluating eval...:  45%|████▍     | 853/1900 [17:19<20:50,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 854/1900 [17:20<20:47,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 855/1900 [17:21<20:43,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 856/1900 [17:22<20:39,  1.19s/it]
+
+
Evaluating eval...:  45%|████▌     | 857/1900 [17:24<20:51,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 858/1900 [17:25<21:14,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 859/1900 [17:26<21:06,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 860/1900 [17:27<21:16,  1.23s/it]
+
+
Evaluating eval...:  45%|████▌     | 861/1900 [17:29<21:41,  1.25s/it]
+
+
Evaluating eval...:  45%|████▌     | 862/1900 [17:30<21:42,  1.25s/it]
+
+
Evaluating eval...:  45%|████▌     | 863/1900 [17:31<21:13,  1.23s/it]
+
+
Evaluating eval...:  45%|████▌     | 864/1900 [17:32<21:01,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 865/1900 [17:33<20:39,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 866/1900 [17:35<20:27,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 867/1900 [17:36<20:55,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 868/1900 [17:37<21:15,  1.24s/it]
+
+
Evaluating eval...:  46%|████▌     | 869/1900 [17:38<20:47,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 870/1900 [17:40<20:46,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 871/1900 [17:41<20:50,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 872/1900 [17:42<20:30,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 873/1900 [17:43<20:32,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 874/1900 [17:44<20:49,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 875/1900 [17:46<20:51,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 876/1900 [17:47<20:49,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 877/1900 [17:48<20:24,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 878/1900 [17:49<20:43,  1.22s/it]
+
+
Evaluating eval...:  46%|████▋     | 879/1900 [17:50<20:30,  1.21s/it]
+
+
Evaluating eval...:  46%|████▋     | 880/1900 [17:52<20:29,  1.21s/it]
+
+
Evaluating eval...:  46%|████▋     | 881/1900 [17:53<20:17,  1.20s/it]
+
+
Evaluating eval...:  46%|████▋     | 882/1900 [17:54<20:21,  1.20s/it]
+
+
Evaluating eval...:  46%|████▋     | 883/1900 [17:55<20:29,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 884/1900 [17:56<20:23,  1.20s/it]
+
+
Evaluating eval...:  47%|████���     | 885/1900 [17:58<20:23,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 886/1900 [17:59<20:10,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 887/1900 [18:00<20:11,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 888/1900 [18:01<20:29,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 889/1900 [18:02<20:22,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 890/1900 [18:04<20:09,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 891/1900 [18:05<20:52,  1.24s/it]
+
+
Evaluating eval...:  47%|████▋     | 892/1900 [18:06<20:54,  1.24s/it]
+
+
Evaluating eval...:  47%|████▋     | 893/1900 [18:07<20:51,  1.24s/it]
+
+
Evaluating eval...:  47%|████▋     | 894/1900 [18:09<20:32,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 895/1900 [18:10<20:35,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 896/1900 [18:11<20:30,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 897/1900 [18:12<20:20,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 898/1900 [18:14<20:38,  1.24s/it]
+
+
Evaluating eval...:  47%|████▋     | 899/1900 [18:15<20:12,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 900/1900 [18:16<20:05,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 901/1900 [18:17<19:54,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 902/1900 [18:18<20:12,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 903/1900 [18:20<20:14,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 904/1900 [18:21<20:13,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 905/1900 [18:22<19:59,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 906/1900 [18:23<19:59,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 907/1900 [18:24<20:15,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 908/1900 [18:26<19:52,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 909/1900 [18:27<19:49,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 910/1900 [18:28<19:35,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 911/1900 [18:29<19:51,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 912/1900 [18:30<19:52,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 913/1900 [18:32<19:46,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 914/1900 [18:33<19:45,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 915/1900 [18:34<20:08,  1.23s/it]
+
+
Evaluating eval...:  48%|████▊     | 916/1900 [18:35<19:53,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 917/1900 [18:36<19:30,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 918/1900 [18:38<19:31,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 919/1900 [18:39<19:29,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 920/1900 [18:40<19:20,  1.18s/it]
+
+
Evaluating eval...:  48%|████▊     | 921/1900 [18:41<19:04,  1.17s/it]
+
+
Evaluating eval...:  49%|████▊     | 922/1900 [18:42<19:01,  1.17s/it]
+
+
Evaluating eval...:  49%|████▊     | 923/1900 [18:44<20:01,  1.23s/it]
+
+
Evaluating eval...:  49%|████▊     | 924/1900 [18:45<19:36,  1.20s/it]
+
+
Evaluating eval...:  49%|████▊     | 925/1900 [18:46<20:03,  1.23s/it]
+
+
Evaluating eval...:  49%|████▊     | 926/1900 [18:47<19:46,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 927/1900 [18:48<19:24,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 928/1900 [18:50<19:34,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 929/1900 [18:51<19:14,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 930/1900 [18:52<19:03,  1.18s/it]
+
+
Evaluating eval...:  49%|████▉     | 931/1900 [18:53<19:08,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 932/1900 [18:54<19:26,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 933/1900 [18:56<19:29,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 934/1900 [18:57<19:16,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 935/1900 [18:58<19:27,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 936/1900 [18:59<19:58,  1.24s/it]
+
+
Evaluating eval...:  49%|████▉     | 937/1900 [19:01<19:50,  1.24s/it]
+
+
Evaluating eval...:  49%|████▉     | 938/1900 [19:02<19:33,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 939/1900 [19:03<19:25,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 940/1900 [19:04<19:25,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 941/1900 [19:05<19:24,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 942/1900 [19:07<19:46,  1.24s/it]
+
+
Evaluating eval...:  50%|████▉     | 943/1900 [19:08<19:23,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 944/1900 [19:09<19:13,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 945/1900 [19:10<18:54,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 946/1900 [19:11<18:59,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 947/1900 [19:13<19:03,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 948/1900 [19:14<18:55,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 949/1900 [19:15<19:03,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 950/1900 [19:16<19:04,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 951/1900 [19:17<19:17,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 952/1900 [19:19<19:29,  1.23s/it]
+
+
Evaluating eval...:  50%|█████     | 953/1900 [19:20<19:07,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 954/1900 [19:21<18:51,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 955/1900 [19:22<18:49,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 956/1900 [19:23<18:37,  1.18s/it]
+
+
Evaluating eval...:  50%|█████     | 957/1900 [19:25<18:36,  1.18s/it]
+
+
Evaluating eval...:  50%|█████     | 958/1900 [19:26<18:35,  1.18s/it]
+
+
Evaluating eval...:  50%|█████     | 959/1900 [19:27<18:36,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 960/1900 [19:28<18:42,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 961/1900 [19:29<19:10,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 962/1900 [19:31<19:00,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 963/1900 [19:32<19:31,  1.25s/it]
+
+
Evaluating eval...:  51%|█████     | 964/1900 [19:33<19:48,  1.27s/it]
+
+
Evaluating eval...:  51%|█████     | 965/1900 [19:35<19:37,  1.26s/it]
+
+
Evaluating eval...:  51%|█████     | 966/1900 [19:36<19:08,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 967/1900 [19:37<18:46,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 968/1900 [19:38<18:34,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 969/1900 [19:39<18:43,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 970/1900 [19:41<18:58,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 971/1900 [19:42<18:38,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 972/1900 [19:43<19:11,  1.24s/it]
+
+
Evaluating eval...:  51%|█████     | 973/1900 [19:44<18:53,  1.22s/it]
+
+
Evaluating eval...:  51%|█████▏    | 974/1900 [19:45<18:41,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 975/1900 [19:47<19:03,  1.24s/it]
+
+
Evaluating eval...:  51%|█████▏    | 976/1900 [19:48<19:31,  1.27s/it]
+
+
Evaluating eval...:  51%|█████▏    | 977/1900 [19:49<18:58,  1.23s/it]
+
+
Evaluating eval...:  51%|█████▏    | 978/1900 [19:50<18:56,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 979/1900 [19:52<18:42,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 980/1900 [19:53<18:37,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 981/1900 [19:54<18:17,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 982/1900 [19:55<18:09,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 983/1900 [19:56<18:28,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 984/1900 [19:58<18:21,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 985/1900 [19:59<18:24,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 986/1900 [20:00<18:23,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 987/1900 [20:01<18:28,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 988/1900 [20:02<18:09,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 989/1900 [20:04<18:12,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 990/1900 [20:05<18:46,  1.24s/it]
+
+
Evaluating eval...:  52%|█████▏    | 991/1900 [20:06<18:29,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 992/1900 [20:07<18:15,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 993/1900 [20:08<18:26,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 994/1900 [20:10<18:11,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 995/1900 [20:11<18:32,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 996/1900 [20:12<18:17,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 997/1900 [20:13<18:10,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 998/1900 [20:14<18:02,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 999/1900 [20:16<17:58,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1000/1900 [20:17<17:49,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1001/1900 [20:18<17:46,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1002/1900 [20:19<17:55,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1003/1900 [20:21<18:16,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1004/1900 [20:22<18:32,  1.24s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1005/1900 [20:23<18:13,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1006/1900 [20:24<18:11,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1007/1900 [20:25<18:01,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1008/1900 [20:27<17:46,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1009/1900 [20:28<17:46,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1010/1900 [20:29<17:46,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1011/1900 [20:30<17:55,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1012/1900 [20:32<18:21,  1.24s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1013/1900 [20:33<18:05,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1014/1900 [20:34<18:28,  1.25s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1015/1900 [20:35<18:10,  1.23s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1016/1900 [20:37<18:37,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1017/1900 [20:38<18:19,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1018/1900 [20:39<18:22,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1019/1900 [20:40<18:40,  1.27s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1020/1900 [20:42<18:27,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1021/1900 [20:43<18:11,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1022/1900 [20:44<18:14,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1023/1900 [20:45<18:18,  1.25s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1024/1900 [20:46<18:07,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1025/1900 [20:48<17:44,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1026/1900 [20:49<17:58,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1027/1900 [20:50<17:53,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1028/1900 [20:51<17:34,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1029/1900 [20:53<17:29,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1030/1900 [20:54<17:20,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1031/1900 [20:55<17:39,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1032/1900 [20:56<17:35,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1033/1900 [20:57<17:21,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1034/1900 [20:59<17:54,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1035/1900 [21:00<17:39,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1036/1900 [21:01<17:34,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1037/1900 [21:02<17:39,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1038/1900 [21:04<17:32,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1039/1900 [21:05<17:43,  1.24s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1040/1900 [21:06<17:34,  1.23s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1041/1900 [21:07<17:23,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1042/1900 [21:08<17:29,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1043/1900 [21:10<17:18,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1044/1900 [21:11<17:19,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1045/1900 [21:12<17:00,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1046/1900 [21:13<16:57,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1047/1900 [21:14<16:54,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1048/1900 [21:16<17:02,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1049/1900 [21:17<17:04,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1050/1900 [21:18<17:48,  1.26s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1051/1900 [21:19<17:45,  1.25s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1052/1900 [21:21<17:36,  1.25s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1053/1900 [21:22<17:35,  1.25s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1054/1900 [21:23<17:19,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1055/1900 [21:24<17:01,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1056/1900 [21:26<17:28,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1057/1900 [21:27<17:45,  1.26s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1058/1900 [21:28<17:33,  1.25s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1059/1900 [21:29<17:05,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1060/1900 [21:30<16:46,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1061/1900 [21:32<16:40,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1062/1900 [21:33<16:38,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1063/1900 [21:34<16:42,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1064/1900 [21:35<16:55,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1065/1900 [21:36<16:54,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1066/1900 [21:38<16:49,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1067/1900 [21:39<16:55,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1068/1900 [21:40<16:47,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1069/1900 [21:41<16:51,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1070/1900 [21:42<16:44,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1071/1900 [21:44<17:03,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1072/1900 [21:45<17:01,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1073/1900 [21:46<16:42,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1074/1900 [21:47<16:35,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1075/1900 [21:49<16:41,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1076/1900 [21:50<16:49,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1077/1900 [21:51<16:49,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1078/1900 [21:52<16:24,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1079/1900 [21:53<16:41,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1080/1900 [21:55<17:22,  1.27s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1081/1900 [21:56<17:14,  1.26s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1082/1900 [21:57<16:54,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1083/1900 [21:59<16:53,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1084/1900 [22:00<16:37,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1085/1900 [22:01<16:41,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1086/1900 [22:02<16:46,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1087/1900 [22:03<16:38,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1088/1900 [22:05<16:29,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1089/1900 [22:06<16:32,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1090/1900 [22:07<16:13,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1091/1900 [22:08<16:07,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1092/1900 [22:10<16:34,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1093/1900 [22:11<16:20,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1094/1900 [22:12<16:16,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1095/1900 [22:13<16:09,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1096/1900 [22:14<15:56,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1097/1900 [22:15<15:46,  1.18s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1098/1900 [22:17<16:08,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1099/1900 [22:18<16:26,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1100/1900 [22:19<16:18,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1101/1900 [22:20<16:08,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1102/1900 [22:21<15:53,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1103/1900 [22:23<16:05,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1104/1900 [22:24<15:56,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1105/1900 [22:25<17:02,  1.29s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1106/1900 [22:27<16:53,  1.28s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1107/1900 [22:28<16:44,  1.27s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1108/1900 [22:29<16:34,  1.26s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1109/1900 [22:30<16:17,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1110/1900 [22:32<16:11,  1.23s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1111/1900 [22:33<16:31,  1.26s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1112/1900 [22:34<16:12,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1113/1900 [22:35<16:03,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1114/1900 [22:36<15:56,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1115/1900 [22:38<15:53,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1116/1900 [22:39<15:54,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1117/1900 [22:40<16:00,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1118/1900 [22:41<15:47,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1119/1900 [22:43<16:06,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1120/1900 [22:44<16:06,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1121/1900 [22:45<16:04,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1122/1900 [22:46<15:43,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1123/1900 [22:48<15:59,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1124/1900 [22:49<15:52,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1125/1900 [22:50<15:40,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1126/1900 [22:51<15:38,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1127/1900 [22:52<15:41,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1128/1900 [22:54<16:04,  1.25s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1129/1900 [22:55<15:49,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1130/1900 [22:56<15:29,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1131/1900 [22:57<15:28,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1132/1900 [22:59<15:45,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1133/1900 [23:00<15:40,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1134/1900 [23:01<15:29,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1135/1900 [23:03<19:25,  1.52s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1136/1900 [23:04<18:02,  1.42s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1137/1900 [23:05<17:04,  1.34s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1138/1900 [23:07<16:40,  1.31s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1139/1900 [23:08<16:12,  1.28s/it]
+
+
Evaluating eval...:  60%|██████    | 1140/1900 [23:09<15:56,  1.26s/it]
+
+
Evaluating eval...:  60%|██████    | 1141/1900 [23:10<15:52,  1.25s/it]
+
+
Evaluating eval...:  60%|██████    | 1142/1900 [23:12<15:30,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1143/1900 [23:13<15:17,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1144/1900 [23:14<15:14,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1145/1900 [23:15<15:18,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1146/1900 [23:16<15:26,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1147/1900 [23:18<15:27,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1148/1900 [23:19<15:17,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1149/1900 [23:20<14:58,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1150/1900 [23:21<15:01,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1151/1900 [23:22<14:53,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1152/1900 [23:24<14:54,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1153/1900 [23:25<15:01,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1154/1900 [23:26<15:01,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1155/1900 [23:27<15:05,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1156/1900 [23:28<15:00,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1157/1900 [23:30<15:03,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1158/1900 [23:31<15:21,  1.24s/it]
+
+
Evaluating eval...:  61%|██████    | 1159/1900 [23:32<15:07,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1160/1900 [23:33<15:06,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1161/1900 [23:35<15:13,  1.24s/it]
+
+
Evaluating eval...:  61%|██████    | 1162/1900 [23:36<15:00,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1163/1900 [23:37<14:53,  1.21s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1164/1900 [23:38<14:40,  1.20s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1165/1900 [23:39<14:32,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1166/1900 [23:41<14:37,  1.20s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1167/1900 [23:42<14:34,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1168/1900 [23:43<14:33,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1169/1900 [23:44<14:26,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1170/1900 [23:45<14:28,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1171/1900 [23:47<14:39,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1172/1900 [23:48<14:40,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1173/1900 [23:49<14:30,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1174/1900 [23:50<14:25,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1175/1900 [23:51<14:40,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1176/1900 [23:53<14:55,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1177/1900 [23:54<14:39,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1178/1900 [23:55<14:25,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1179/1900 [23:56<14:28,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1180/1900 [23:58<14:39,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1181/1900 [23:59<14:22,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1182/1900 [24:00<14:37,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1183/1900 [24:01<14:37,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1184/1900 [24:02<14:40,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1185/1900 [24:04<14:36,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1186/1900 [24:05<14:37,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1187/1900 [24:06<14:24,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1188/1900 [24:07<14:12,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1189/1900 [24:08<14:03,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1190/1900 [24:09<13:55,  1.18s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1191/1900 [24:11<14:15,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1192/1900 [24:12<14:24,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1193/1900 [24:13<14:19,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1194/1900 [24:15<14:34,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1195/1900 [24:16<14:26,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1196/1900 [24:17<14:14,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1197/1900 [24:18<14:11,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1198/1900 [24:19<14:05,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1199/1900 [24:21<14:20,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1200/1900 [24:22<14:10,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1201/1900 [24:23<14:04,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1202/1900 [24:24<13:51,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1203/1900 [24:25<14:04,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1204/1900 [24:27<14:11,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1205/1900 [24:28<14:09,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1206/1900 [24:29<14:21,  1.24s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1207/1900 [24:30<14:06,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1208/1900 [24:31<13:59,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1209/1900 [24:33<13:41,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1210/1900 [24:34<13:52,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1211/1900 [24:35<14:00,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1212/1900 [24:36<14:08,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1213/1900 [24:38<13:54,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1214/1900 [24:39<13:42,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1215/1900 [24:40<13:34,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1216/1900 [24:41<13:39,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1217/1900 [24:42<13:43,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1218/1900 [24:44<13:54,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1219/1900 [24:45<13:44,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1220/1900 [24:46<13:49,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1221/1900 [24:47<13:40,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1222/1900 [24:48<13:30,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1223/1900 [24:50<13:25,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1224/1900 [24:51<13:13,  1.17s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1225/1900 [24:52<13:20,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1226/1900 [24:53<13:18,  1.18s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1227/1900 [24:54<13:18,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1228/1900 [24:55<13:07,  1.17s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1229/1900 [24:57<13:02,  1.17s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1230/1900 [24:58<13:09,  1.18s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1231/1900 [24:59<13:12,  1.18s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1232/1900 [25:00<13:09,  1.18s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1233/1900 [25:01<13:04,  1.18s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1234/1900 [25:02<13:06,  1.18s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1235/1900 [25:04<13:17,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1236/1900 [25:05<13:07,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1237/1900 [25:06<13:03,  1.18s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1238/1900 [25:07<12:55,  1.17s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1239/1900 [25:09<13:16,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1240/1900 [25:10<13:43,  1.25s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1241/1900 [25:11<13:23,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1242/1900 [25:12<13:12,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1243/1900 [25:13<13:20,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1244/1900 [25:15<13:04,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1245/1900 [25:16<12:55,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1246/1900 [25:17<13:00,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1247/1900 [25:18<12:51,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1248/1900 [25:19<12:45,  1.17s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1249/1900 [25:20<12:57,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1250/1900 [25:22<12:54,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1251/1900 [25:23<12:49,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1252/1900 [25:24<12:45,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1253/1900 [25:25<12:58,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1254/1900 [25:27<13:07,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1255/1900 [25:28<13:03,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1256/1900 [25:29<13:02,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1257/1900 [25:30<12:48,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1258/1900 [25:31<12:52,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1259/1900 [25:32<12:38,  1.18s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1260/1900 [25:34<12:40,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1261/1900 [25:35<12:42,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1262/1900 [25:36<12:36,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1263/1900 [25:37<12:40,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1264/1900 [25:38<12:45,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1265/1900 [25:40<12:49,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1266/1900 [25:41<12:59,  1.23s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1267/1900 [25:42<12:49,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1268/1900 [25:43<12:40,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1269/1900 [25:45<12:42,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1270/1900 [25:46<12:34,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1271/1900 [25:47<12:37,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1272/1900 [25:48<12:28,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1273/1900 [25:49<12:22,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1274/1900 [25:50<12:18,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1275/1900 [25:52<12:14,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1276/1900 [25:53<12:17,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1277/1900 [25:54<12:13,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1278/1900 [25:55<12:09,  1.17s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1279/1900 [25:56<12:04,  1.17s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1280/1900 [25:57<12:04,  1.17s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1281/1900 [25:59<12:00,  1.16s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1282/1900 [26:00<11:57,  1.16s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1283/1900 [26:01<12:01,  1.17s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1284/1900 [26:02<12:05,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1285/1900 [26:03<12:07,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1286/1900 [26:05<12:05,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1287/1900 [26:06<12:29,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1288/1900 [26:07<12:30,  1.23s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1289/1900 [26:08<12:19,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1290/1900 [26:09<12:06,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1291/1900 [26:11<12:01,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1292/1900 [26:12<12:03,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1293/1900 [26:13<12:06,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1294/1900 [26:14<12:14,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1295/1900 [26:15<12:03,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1296/1900 [26:17<12:06,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1297/1900 [26:18<11:57,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1298/1900 [26:19<12:01,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1299/1900 [26:20<12:00,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1300/1900 [26:21<12:06,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1301/1900 [26:23<12:09,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1302/1900 [26:24<12:06,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1303/1900 [26:25<12:04,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1304/1900 [26:26<11:58,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1305/1900 [26:27<11:47,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1306/1900 [26:29<11:49,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1307/1900 [26:30<11:42,  1.18s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1308/1900 [26:31<12:00,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1309/1900 [26:32<11:52,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1310/1900 [26:33<11:43,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1311/1900 [26:35<11:45,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1312/1900 [26:36<11:44,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1313/1900 [26:37<11:45,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1314/1900 [26:38<11:35,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1315/1900 [26:39<11:30,  1.18s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1316/1900 [26:41<11:45,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1317/1900 [26:42<11:37,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1318/1900 [26:43<11:41,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1319/1900 [26:44<11:30,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1320/1900 [26:45<11:24,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1321/1900 [26:47<11:33,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1322/1900 [26:48<11:24,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1323/1900 [26:49<11:27,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1324/1900 [26:50<11:20,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1325/1900 [26:51<11:12,  1.17s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1326/1900 [26:52<11:15,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1327/1900 [26:54<11:13,  1.17s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1328/1900 [26:55<11:35,  1.22s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1329/1900 [26:56<11:26,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1330/1900 [26:57<11:28,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1331/1900 [26:58<11:19,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1332/1900 [27:00<11:17,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1333/1900 [27:01<11:15,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1334/1900 [27:02<11:14,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1335/1900 [27:03<11:12,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1336/1900 [27:04<11:12,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1337/1900 [27:06<11:22,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1338/1900 [27:07<11:13,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1339/1900 [27:08<11:08,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1340/1900 [27:09<11:03,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1341/1900 [27:10<10:57,  1.18s/it]
+
+
Evaluating eval...:  71%|███████   | 1342/1900 [27:12<11:04,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1343/1900 [27:13<10:59,  1.18s/it]
+
+
Evaluating eval...:  71%|███████   | 1344/1900 [27:14<10:58,  1.18s/it]
+
+
Evaluating eval...:  71%|███████   | 1345/1900 [27:15<11:04,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1346/1900 [27:16<11:28,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1347/1900 [27:18<11:16,  1.22s/it]
+
+
Evaluating eval...:  71%|███████   | 1348/1900 [27:19<11:02,  1.20s/it]
+
+
Evaluating eval...:  71%|███████   | 1349/1900 [27:20<11:15,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1350/1900 [27:21<11:08,  1.22s/it]
+
+
Evaluating eval...:  71%|███████   | 1351/1900 [27:23<11:07,  1.22s/it]
+
+
Evaluating eval...:  71%|███████   | 1352/1900 [27:24<11:04,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1353/1900 [27:25<11:10,  1.23s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1354/1900 [27:26<11:13,  1.23s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1355/1900 [27:27<11:08,  1.23s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1356/1900 [27:29<11:05,  1.22s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1357/1900 [27:30<10:53,  1.20s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1358/1900 [27:31<10:48,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1359/1900 [27:32<10:49,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1360/1900 [27:33<10:40,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1361/1900 [27:35<10:57,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1362/1900 [27:36<10:45,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1363/1900 [27:37<10:57,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1364/1900 [27:38<10:46,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1365/1900 [27:39<10:38,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1366/1900 [27:41<10:32,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1367/1900 [27:42<10:33,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1368/1900 [27:43<10:44,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1369/1900 [27:44<10:48,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1370/1900 [27:46<10:50,  1.23s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1371/1900 [27:47<10:49,  1.23s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1372/1900 [27:48<10:37,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1373/1900 [27:49<10:28,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1374/1900 [27:50<10:24,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1375/1900 [27:51<10:23,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1376/1900 [27:53<10:22,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1377/1900 [27:54<10:24,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1378/1900 [27:55<10:15,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1379/1900 [27:56<10:17,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1380/1900 [27:57<10:19,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1381/1900 [27:59<10:19,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1382/1900 [28:00<10:16,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1383/1900 [28:01<10:13,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1384/1900 [28:02<10:10,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1385/1900 [28:03<10:09,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1386/1900 [28:05<10:12,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1387/1900 [28:06<10:04,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1388/1900 [28:07<10:01,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1389/1900 [28:08<09:55,  1.17s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1390/1900 [28:09<10:10,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1391/1900 [28:10<10:09,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1392/1900 [28:12<10:06,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1393/1900 [28:13<09:59,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1394/1900 [28:14<10:08,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1395/1900 [28:15<10:01,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1396/1900 [28:16<09:58,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1397/1900 [28:18<09:59,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1398/1900 [28:19<10:03,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1399/1900 [28:20<09:58,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1400/1900 [28:21<09:49,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1401/1900 [28:22<10:04,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1402/1900 [28:24<09:51,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1403/1900 [28:25<09:45,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1404/1900 [28:26<09:42,  1.17s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1405/1900 [28:27<09:35,  1.16s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1406/1900 [28:28<09:36,  1.17s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1407/1900 [28:29<09:42,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1408/1900 [28:31<09:52,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1409/1900 [28:32<09:48,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1410/1900 [28:33<09:43,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1411/1900 [28:34<09:43,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1412/1900 [28:35<09:39,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1413/1900 [28:37<09:38,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1414/1900 [28:38<09:38,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1415/1900 [28:39<09:32,  1.18s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1416/1900 [28:40<09:30,  1.18s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1417/1900 [28:41<09:27,  1.17s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1418/1900 [28:42<09:23,  1.17s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1419/1900 [28:44<09:39,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1420/1900 [28:45<09:37,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1421/1900 [28:46<09:37,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1422/1900 [28:47<09:44,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1423/1900 [28:49<09:37,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1424/1900 [28:50<09:38,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1425/1900 [28:51<09:36,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1426/1900 [28:52<09:30,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1427/1900 [28:53<09:28,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1428/1900 [28:55<09:38,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1429/1900 [28:56<09:35,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1430/1900 [28:57<09:32,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1431/1900 [28:58<09:35,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1432/1900 [29:01<11:59,  1.54s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1433/1900 [29:02<11:09,  1.43s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1434/1900 [29:03<10:37,  1.37s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1435/1900 [29:04<10:11,  1.32s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1436/1900 [29:05<09:59,  1.29s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1437/1900 [29:07<09:44,  1.26s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1438/1900 [29:08<09:31,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1439/1900 [29:09<09:22,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1440/1900 [29:10<09:21,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1441/1900 [29:11<09:11,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1442/1900 [29:13<09:12,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1443/1900 [29:14<09:15,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1444/1900 [29:15<09:06,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1445/1900 [29:16<09:04,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1446/1900 [29:17<09:02,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1447/1900 [29:19<08:58,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1448/1900 [29:20<08:55,  1.18s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1449/1900 [29:21<09:03,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1450/1900 [29:22<09:05,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1451/1900 [29:23<09:02,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1452/1900 [29:25<08:54,  1.19s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1453/1900 [29:26<08:52,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1454/1900 [29:27<09:09,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1455/1900 [29:28<09:00,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1456/1900 [29:29<08:58,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1457/1900 [29:31<08:55,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1458/1900 [29:32<08:54,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1459/1900 [29:33<08:45,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1460/1900 [29:34<08:40,  1.18s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1461/1900 [29:35<08:38,  1.18s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1462/1900 [29:37<08:37,  1.18s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1463/1900 [29:38<08:36,  1.18s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1464/1900 [29:39<08:38,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1465/1900 [29:40<08:35,  1.19s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1466/1900 [29:41<08:44,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1467/1900 [29:43<08:37,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1468/1900 [29:44<08:52,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1469/1900 [29:45<08:45,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1470/1900 [29:46<08:34,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1471/1900 [29:47<08:36,  1.20s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1472/1900 [29:49<08:29,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1473/1900 [29:50<08:29,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1474/1900 [29:51<08:28,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1475/1900 [29:52<08:25,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1476/1900 [29:53<08:26,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1477/1900 [29:55<08:28,  1.20s/it]
+
+
Evaluating eval...:  78%|██��████▊  | 1478/1900 [29:56<08:31,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1479/1900 [29:57<08:58,  1.28s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1480/1900 [29:58<08:41,  1.24s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1481/1900 [30:00<08:37,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1482/1900 [30:01<08:31,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1483/1900 [30:02<08:20,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1484/1900 [30:03<08:22,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1485/1900 [30:04<08:24,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1486/1900 [30:06<08:14,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1487/1900 [30:07<08:19,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1488/1900 [30:08<08:11,  1.19s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1489/1900 [30:09<08:05,  1.18s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1490/1900 [30:10<08:05,  1.18s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1491/1900 [30:11<08:00,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1492/1900 [30:13<08:02,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1493/1900 [30:14<08:05,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1494/1900 [30:15<08:00,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1495/1900 [30:16<07:56,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1496/1900 [30:17<07:51,  1.17s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1497/1900 [30:18<07:47,  1.16s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1498/1900 [30:20<07:50,  1.17s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1499/1900 [30:21<08:00,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1500/1900 [30:22<08:00,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1501/1900 [30:23<07:54,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1502/1900 [30:24<07:51,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1503/1900 [30:26<07:53,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1504/1900 [30:27<07:47,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1505/1900 [30:28<07:45,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1506/1900 [30:29<07:48,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1507/1900 [30:30<07:45,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1508/1900 [30:32<07:48,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1509/1900 [30:33<07:52,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1510/1900 [30:34<07:48,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1511/1900 [30:35<07:47,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1512/1900 [30:36<07:53,  1.22s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1513/1900 [30:38<07:54,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1514/1900 [30:39<07:48,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1515/1900 [30:40<08:01,  1.25s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1516/1900 [30:42<08:05,  1.27s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1517/1900 [30:43<07:51,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1518/1900 [30:44<07:40,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1519/1900 [30:45<07:30,  1.18s/it]
+
+
Evaluating eval...:  80%|████████  | 1520/1900 [30:46<07:31,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1521/1900 [30:47<07:33,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1522/1900 [30:49<07:28,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1523/1900 [30:50<07:32,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1524/1900 [30:51<07:33,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1525/1900 [30:52<07:35,  1.22s/it]
+
+
Evaluating eval...:  80%|████████  | 1526/1900 [30:53<07:27,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1527/1900 [30:55<07:26,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1528/1900 [30:56<07:34,  1.22s/it]
+
+
Evaluating eval...:  80%|████████  | 1529/1900 [30:57<07:27,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1530/1900 [30:58<07:27,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1531/1900 [30:59<07:27,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1532/1900 [31:01<07:31,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1533/1900 [31:02<07:23,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1534/1900 [31:03<07:22,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1535/1900 [31:04<07:12,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1536/1900 [31:05<07:08,  1.18s/it]
+
+
Evaluating eval...:  81%|████████  | 1537/1900 [31:07<07:11,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1538/1900 [31:08<07:07,  1.18s/it]
+
+
Evaluating eval...:  81%|████████  | 1539/1900 [31:09<07:21,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1540/1900 [31:10<07:14,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1541/1900 [31:12<07:23,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1542/1900 [31:13<07:13,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1543/1900 [31:14<07:10,  1.20s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1544/1900 [31:15<07:08,  1.20s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1545/1900 [31:16<07:04,  1.20s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1546/1900 [31:17<07:03,  1.20s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1547/1900 [31:19<07:10,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1548/1900 [31:20<07:03,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1549/1900 [31:21<06:56,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1550/1900 [31:22<07:03,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1551/1900 [31:24<07:04,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1552/1900 [31:25<06:56,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1553/1900 [31:26<06:53,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1554/1900 [31:27<06:52,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1555/1900 [31:28<06:50,  1.19s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1556/1900 [31:30<07:01,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1557/1900 [31:31<06:56,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1558/1900 [31:32<07:07,  1.25s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1559/1900 [31:33<07:07,  1.25s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1560/1900 [31:35<06:55,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1561/1900 [31:36<06:59,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1562/1900 [31:37<07:01,  1.25s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1563/1900 [31:38<06:57,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1564/1900 [31:39<06:49,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1565/1900 [31:41<06:44,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1566/1900 [31:42<06:42,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1567/1900 [31:43<06:39,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1568/1900 [31:45<08:26,  1.53s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1569/1900 [31:47<07:58,  1.45s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1570/1900 [31:48<07:37,  1.39s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1571/1900 [31:49<07:14,  1.32s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1572/1900 [31:50<07:05,  1.30s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1573/1900 [31:51<06:53,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1574/1900 [31:53<06:44,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1575/1900 [31:54<06:37,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1576/1900 [31:55<06:31,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1577/1900 [31:56<06:36,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1578/1900 [31:57<06:30,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1579/1900 [31:59<06:26,  1.20s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1580/1900 [32:00<06:31,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1581/1900 [32:01<06:34,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1582/1900 [32:02<06:32,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1583/1900 [32:04<06:29,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1584/1900 [32:05<06:38,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1585/1900 [32:06<06:36,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1586/1900 [32:07<06:31,  1.25s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1587/1900 [32:09<06:21,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1588/1900 [32:10<06:12,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1589/1900 [32:11<06:15,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1590/1900 [32:12<06:15,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1591/1900 [32:13<06:20,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1592/1900 [32:15<06:12,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1593/1900 [32:16<06:14,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1594/1900 [32:17<06:14,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1595/1900 [32:18<06:10,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1596/1900 [32:19<06:10,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1597/1900 [32:21<06:10,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1598/1900 [32:22<06:02,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1599/1900 [32:23<05:55,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1600/1900 [32:24<05:52,  1.17s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1601/1900 [32:25<05:49,  1.17s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1602/1900 [32:26<05:50,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1603/1900 [32:28<05:50,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1604/1900 [32:29<05:55,  1.20s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1605/1900 [32:30<05:48,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1606/1900 [32:31<05:49,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1607/1900 [32:32<05:46,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1608/1900 [32:34<05:46,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1609/1900 [32:35<05:54,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1610/1900 [32:36<05:48,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1611/1900 [32:37<05:41,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1612/1900 [32:38<05:36,  1.17s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1613/1900 [32:39<05:31,  1.15s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1614/1900 [32:41<05:35,  1.17s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1615/1900 [32:42<05:34,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1616/1900 [32:43<05:33,  1.17s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1617/1900 [32:44<05:34,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1618/1900 [32:45<05:36,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1619/1900 [32:47<05:36,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1620/1900 [32:48<05:34,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1621/1900 [32:49<05:31,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1622/1900 [32:50<05:28,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1623/1900 [32:51<05:27,  1.18s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1624/1900 [32:53<05:24,  1.17s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1625/1900 [32:54<05:24,  1.18s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1626/1900 [32:55<05:30,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1627/1900 [32:56<05:32,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1628/1900 [32:57<05:31,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1629/1900 [32:59<05:26,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1630/1900 [33:00<05:23,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1631/1900 [33:01<05:32,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1632/1900 [33:02<05:22,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1633/1900 [33:03<05:20,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1634/1900 [33:05<05:20,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1635/1900 [33:06<05:18,  1.20s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1636/1900 [33:07<05:21,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1637/1900 [33:08<05:20,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1638/1900 [33:10<05:12,  1.19s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1639/1900 [33:11<05:15,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1640/1900 [33:12<05:15,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1641/1900 [33:13<05:13,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1642/1900 [33:14<05:13,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1643/1900 [33:16<05:13,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1644/1900 [33:17<05:06,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1645/1900 [33:18<05:00,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1646/1900 [33:19<05:03,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1647/1900 [33:20<05:01,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1648/1900 [33:22<05:01,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1649/1900 [33:23<04:59,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1650/1900 [33:24<05:02,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1651/1900 [33:25<04:57,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1652/1900 [33:26<04:53,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1653/1900 [33:27<04:51,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1654/1900 [33:29<04:53,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1655/1900 [33:30<04:59,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1656/1900 [33:31<04:57,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1657/1900 [33:32<04:57,  1.23s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1658/1900 [33:34<04:59,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1659/1900 [33:35<05:02,  1.25s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1660/1900 [33:36<04:59,  1.25s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1661/1900 [33:37<04:56,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1662/1900 [33:39<04:51,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1663/1900 [33:40<04:45,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1664/1900 [33:41<04:48,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1665/1900 [33:42<04:44,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1666/1900 [33:45<05:58,  1.53s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1667/1900 [33:46<05:34,  1.44s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1668/1900 [33:47<05:19,  1.38s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1669/1900 [33:48<05:05,  1.32s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1670/1900 [33:49<04:58,  1.30s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1671/1900 [33:51<04:49,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1672/1900 [33:52<04:45,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1673/1900 [33:53<04:49,  1.27s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1674/1900 [33:54<04:47,  1.27s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1675/1900 [33:56<04:41,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1676/1900 [33:57<04:35,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1677/1900 [33:58<04:31,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1678/1900 [33:59<04:25,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1679/1900 [34:00<04:27,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1680/1900 [34:02<04:25,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1681/1900 [34:03<04:25,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1682/1900 [34:04<04:21,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1683/1900 [34:05<04:23,  1.21s/it]
+
+
Evaluating eval...:  89%|██████��█▊ | 1684/1900 [34:06<04:20,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1685/1900 [34:08<04:14,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1686/1900 [34:09<04:15,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1687/1900 [34:10<04:17,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1688/1900 [34:11<04:16,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1689/1900 [34:12<04:14,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1690/1900 [34:14<04:13,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1691/1900 [34:15<04:15,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1692/1900 [34:16<04:12,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1693/1900 [34:17<04:14,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1694/1900 [34:19<04:16,  1.24s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1695/1900 [34:20<04:10,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1696/1900 [34:21<04:05,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1697/1900 [34:22<04:07,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1698/1900 [34:23<04:09,  1.24s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1699/1900 [34:25<04:03,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1700/1900 [34:26<04:02,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1701/1900 [34:27<04:03,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1702/1900 [34:28<04:04,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1703/1900 [34:30<04:03,  1.24s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1704/1900 [34:31<03:58,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1705/1900 [34:32<03:53,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1706/1900 [34:33<03:51,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1707/1900 [34:34<03:48,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1708/1900 [34:35<03:50,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1709/1900 [34:37<03:48,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1710/1900 [34:38<03:48,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1711/1900 [34:39<03:44,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1712/1900 [34:40<03:42,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1713/1900 [34:41<03:38,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1714/1900 [34:43<03:35,  1.16s/it]
+
+
Evaluating eval...:  90%|█████████ | 1715/1900 [34:44<03:37,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1716/1900 [34:45<03:37,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1717/1900 [34:46<03:43,  1.22s/it]
+
+
Evaluating eval...:  90%|█████████ | 1718/1900 [34:47<03:44,  1.23s/it]
+
+
Evaluating eval...:  90%|█████████ | 1719/1900 [34:49<03:39,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1720/1900 [34:50<03:40,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1721/1900 [34:51<03:38,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1722/1900 [34:52<03:38,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1723/1900 [34:54<03:33,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1724/1900 [34:55<03:41,  1.26s/it]
+
+
Evaluating eval...:  91%|█████████ | 1725/1900 [34:56<03:37,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1726/1900 [34:57<03:34,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1727/1900 [34:59<03:33,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1728/1900 [35:00<03:29,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1729/1900 [35:01<03:25,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████ | 1730/1900 [35:02<03:28,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1731/1900 [35:03<03:24,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1732/1900 [35:05<03:22,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1733/1900 [35:06<03:22,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1734/1900 [35:07<03:18,  1.20s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1735/1900 [35:08<03:17,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1736/1900 [35:09<03:19,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1737/1900 [35:11<03:17,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1738/1900 [35:12<03:14,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1739/1900 [35:13<03:13,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1740/1900 [35:14<03:12,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1741/1900 [35:15<03:13,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1742/1900 [35:17<03:08,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1743/1900 [35:18<03:08,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1744/1900 [35:19<03:07,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1745/1900 [35:20<03:04,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1746/1900 [35:21<03:09,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1747/1900 [35:23<03:05,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1748/1900 [35:24<03:04,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1749/1900 [35:25<03:04,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1750/1900 [35:26<03:05,  1.24s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1751/1900 [35:28<03:02,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1752/1900 [35:29<02:59,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1753/1900 [35:30<02:55,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1754/1900 [35:31<02:53,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1755/1900 [35:32<02:55,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1756/1900 [35:34<02:55,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1757/1900 [35:35<02:55,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1758/1900 [35:36<02:53,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1759/1900 [35:37<02:49,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1760/1900 [35:38<02:45,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1761/1900 [35:40<02:44,  1.18s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1762/1900 [35:41<02:44,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1763/1900 [35:42<02:42,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1764/1900 [35:43<02:45,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1765/1900 [35:44<02:44,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1766/1900 [35:46<02:43,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1767/1900 [35:47<02:41,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1768/1900 [35:48<02:43,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1769/1900 [35:49<02:42,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1770/1900 [35:51<02:43,  1.26s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1771/1900 [35:52<02:40,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1772/1900 [35:53<02:36,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1773/1900 [35:54<02:39,  1.25s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1774/1900 [35:56<02:35,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1775/1900 [35:57<02:31,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1776/1900 [35:58<02:28,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1777/1900 [35:59<02:25,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1778/1900 [36:00<02:25,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1779/1900 [36:01<02:22,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1780/1900 [36:03<02:21,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1781/1900 [36:04<02:20,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1782/1900 [36:05<02:22,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1783/1900 [36:06<02:23,  1.23s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1784/1900 [36:08<02:21,  1.22s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1785/1900 [36:09<02:17,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1786/1900 [36:10<02:15,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1787/1900 [36:11<02:13,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1788/1900 [36:12<02:11,  1.17s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1789/1900 [36:13<02:09,  1.17s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1790/1900 [36:15<02:11,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1791/1900 [36:16<02:10,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1792/1900 [36:17<02:08,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1793/1900 [36:18<02:11,  1.23s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1794/1900 [36:19<02:08,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1795/1900 [36:21<02:05,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1796/1900 [36:22<02:04,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1797/1900 [36:23<02:02,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1798/1900 [36:24<02:03,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1799/1900 [36:25<02:01,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1800/1900 [36:27<01:59,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1801/1900 [36:28<01:56,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1802/1900 [36:29<01:56,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1803/1900 [36:30<01:57,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1804/1900 [36:31<01:54,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1805/1900 [36:33<01:52,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1806/1900 [36:34<01:51,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1807/1900 [36:35<01:50,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1808/1900 [36:36<01:48,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1809/1900 [36:37<01:46,  1.17s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1810/1900 [36:38<01:46,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1811/1900 [36:40<01:45,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1812/1900 [36:41<01:44,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1813/1900 [36:42<01:43,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1814/1900 [36:43<01:43,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1815/1900 [36:44<01:40,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1816/1900 [36:46<01:40,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1817/1900 [36:47<01:42,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1818/1900 [36:48<01:39,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1819/1900 [36:49<01:37,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1820/1900 [36:50<01:36,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1821/1900 [36:52<01:35,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1822/1900 [36:53<01:33,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1823/1900 [36:54<01:31,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1824/1900 [36:55<01:30,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1825/1900 [36:56<01:30,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1826/1900 [36:58<01:29,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1827/1900 [36:59<01:29,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1828/1900 [37:00<01:28,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1829/1900 [37:02<01:28,  1.25s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1830/1900 [37:03<01:25,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1831/1900 [37:04<01:23,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1832/1900 [37:05<01:21,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1833/1900 [37:06<01:19,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1834/1900 [37:07<01:18,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1835/1900 [37:09<01:17,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1836/1900 [37:10<01:16,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1837/1900 [37:11<01:15,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1838/1900 [37:12<01:14,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1839/1900 [37:13<01:12,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1840/1900 [37:15<01:12,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1841/1900 [37:16<01:11,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1842/1900 [37:17<01:10,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1843/1900 [37:18<01:08,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1844/1900 [37:19<01:07,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1845/1900 [37:21<01:05,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1846/1900 [37:22<01:04,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1847/1900 [37:23<01:03,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1848/1900 [37:24<01:02,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1849/1900 [37:25<01:01,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1850/1900 [37:27<01:00,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1851/1900 [37:28<00:59,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1852/1900 [37:29<00:57,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1853/1900 [37:30<00:56,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1854/1900 [37:31<00:54,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1855/1900 [37:33<00:55,  1.23s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1856/1900 [37:34<00:53,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1857/1900 [37:35<00:51,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1858/1900 [37:36<00:50,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1859/1900 [37:37<00:49,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1860/1900 [37:39<00:48,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1861/1900 [37:40<00:46,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1862/1900 [37:41<00:45,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1863/1900 [37:42<00:44,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1864/1900 [37:43<00:43,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1865/1900 [37:45<00:41,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1866/1900 [37:46<00:41,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1867/1900 [37:47<00:40,  1.23s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1868/1900 [37:48<00:39,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1869/1900 [37:50<00:38,  1.24s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1870/1900 [37:51<00:36,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1871/1900 [37:52<00:35,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1872/1900 [37:53<00:34,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1873/1900 [37:54<00:32,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1874/1900 [37:56<00:31,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1875/1900 [37:57<00:30,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1876/1900 [37:58<00:29,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1877/1900 [37:59<00:27,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1878/1900 [38:00<00:26,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1879/1900 [38:02<00:24,  1.18s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1880/1900 [38:03<00:23,  1.18s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1881/1900 [38:04<00:22,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1882/1900 [38:05<00:22,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1883/1900 [38:07<00:21,  1.25s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1884/1900 [38:08<00:20,  1.26s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1885/1900 [38:09<00:18,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1886/1900 [38:10<00:17,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1887/1900 [38:11<00:15,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1888/1900 [38:13<00:14,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1889/1900 [38:14<00:13,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1890/1900 [38:15<00:11,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1891/1900 [38:16<00:10,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1892/1900 [38:17<00:09,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1893/1900 [38:19<00:08,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1894/1900 [38:20<00:07,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1895/1900 [38:21<00:05,  1.20s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1896/1900 [38:22<00:04,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1897/1900 [38:23<00:03,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1898/1900 [38:24<00:02,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1899/1900 [38:26<00:01,  1.19s/it]
+
+
Evaluating eval...: 100%|██████████| 1900/1900 [38:27<00:00,  1.31s/it]
Evaluating eval...: 100%|██████████| 1900/1900 [38:27<00:00,  1.21s/it]
+Eval results for step (10000 / 100000 | Eval Loss: 1.414140224456787 | Eval wer: 36.426182180455754 | Eval wer_ortho: 39.79332947133539 |)
+
                                                                             
Eval results for step (10000 / 100000 | Eval Loss: 1.414140224456787 | Eval wer: 36.426182180455754 | Eval wer_ortho: 39.79332947133539 |)
+
Train steps ... :  10%|█         | 10000/100000 [3:08:36<14:39:49,  1.70it/s]
Train steps ... :  10%|█         | 10001/100000 [3:08:37<18846:18:30, 753.86s/it]
Train steps ... :  10%|█         | 10002/100000 [3:08:37<13196:38:06, 527.88s/it]
Train steps ... :  10%|█         | 10003/100000 [3:08:38<9241:55:44, 369.69s/it] 
Train steps ... :  10%|█         | 10004/100000 [3:08:38<6473:39:39, 258.96s/it]
Train steps ... :  10%|█         | 10005/100000 [3:08:39<4535:53:07, 181.45s/it]
Train steps ... :  10%|█         | 10006/100000 [3:08:40<3179:27:40, 127.19s/it]
Train steps ... :  10%|█         | 10007/100000 [3:08:40<2229:58:55, 89.21s/it] 
Train steps ... :  10%|█         | 10008/100000 [3:08:41<1565:21:02, 62.62s/it]
Train steps ... :  10%|█         | 10009/100000 [3:08:41<1100:06:10, 44.01s/it]
Train steps ... :  10%|█         | 10010/100000 [3:08:42<774:27:05, 30.98s/it] 
Train steps ... :  10%|█         | 10011/100000 [3:08:42<546:28:42, 21.86s/it]
Train steps ... :  10%|█         | 10012/100000 [3:08:43<386:54:40, 15.48s/it]
Train steps ... :  10%|█         | 10013/100000 [3:08:44<275:12:39, 11.01s/it]
Train steps ... :  10%|█         | 10014/100000 [3:08:44<197:02:24,  7.88s/it]
Train steps ... :  10%|█         | 10015/100000 [3:08:45<142:19:03,  5.69s/it]
Train steps ... :  10%|█         | 10016/100000 [3:08:45<103:59:39,  4.16s/it]
Train steps ... :  10%|█         | 10017/100000 [3:08:46<77:11:45,  3.09s/it] 
Train steps ... :  10%|█         | 10018/100000 [3:08:47<58:24:39,  2.34s/it]
Train steps ... :  10%|█         | 10019/100000 [3:08:47<45:15:29,  1.81s/it]
Train steps ... :  10%|█         | 10020/100000 [3:08:48<36:03:47,  1.44s/it]
Train steps ... :  10%|█         | 10021/100000 [3:08:48<29:37:59,  1.19s/it]
Train steps ... :  10%|█         | 10022/100000 [3:08:49<25:06:31,  1.00s/it]
Train steps ... :  10%|█         | 10023/100000 [3:08:49<21:57:41,  1.14it/s]
Train steps ... :  10%|█         | 10024/100000 [3:08:50<19:45:57,  1.26it/s]
Train steps ... :  10%|█         | 10025/100000 [3:08:51<18:13:32,  1.37it/s]Step... (10025 / 100000 | Loss: 1.0956380367279053, Learning Rate: 9.042713567839196e-05)
+
                                                                             
Step... (10025 / 100000 | Loss: 1.2013964653015137, Learning Rate: 9.042713567839196e-05)
+
Train steps ... :  10%|█         | 10025/100000 [3:08:51<18:13:32,  1.37it/s]
Train steps ... :  10%|█         | 10026/100000 [3:08:51<17:08:00,  1.46it/s]
Train steps ... :  10%|█         | 10027/100000 [3:08:52<16:23:13,  1.53it/s]
Train steps ... :  10%|█         | 10028/100000 [3:08:52<15:50:40,  1.58it/s]
Train steps ... :  10%|█         | 10029/100000 [3:08:53<15:27:32,  1.62it/s]
Train steps ... :  10%|█         | 10030/100000 [3:08:54<15:12:22,  1.64it/s]
Train steps ... :  10%|█         | 10031/100000 [3:08:54<15:00:50,  1.66it/s]
Train steps ... :  10%|█         | 10032/100000 [3:08:55<14:52:53,  1.68it/s]
Train steps ... :  10%|█         | 10033/100000 [3:08:55<14:47:30,  1.69it/s]
Train steps ... :  10%|█         | 10034/100000 [3:08:56<14:43:24,  1.70it/s]
Train steps ... :  10%|█         | 10035/100000 [3:08:56<14:41:29,  1.70it/s]
Train steps ... :  10%|█         | 10036/100000 [3:08:57<14:39:47,  1.70it/s]
Train steps ... :  10%|█         | 10037/100000 [3:08:58<14:38:19,  1.71it/s]
Train steps ... :  10%|█         | 10038/100000 [3:08:58<14:37:10,  1.71it/s]
Train steps ... :  10%|█         | 10039/100000 [3:08:59<14:37:32,  1.71it/s]
Train steps ... :  10%|█         | 10040/100000 [3:08:59<14:37:38,  1.71it/s]
Train steps ... :  10%|█         | 10041/100000 [3:09:00<14:37:12,  1.71it/s]
Train steps ... :  10%|█         | 10042/100000 [3:09:01<14:38:23,  1.71it/s]
Train steps ... :  10%|█         | 10043/100000 [3:09:01<14:38:31,  1.71it/s]
Train steps ... :  10%|█         | 10044/100000 [3:09:02<14:37:38,  1.71it/s]
Train steps ... :  10%|█         | 10045/100000 [3:09:02<14:38:16,  1.71it/s]
Train steps ... :  10%|█         | 10046/100000 [3:09:03<14:40:44,  1.70it/s]
Train steps ... :  10%|█         | 10047/100000 [3:09:03<14:37:39,  1.71it/s]
Train steps ... :  10%|█         | 10048/100000 [3:09:04<14:37:26,  1.71it/s]
Train steps ... :  10%|█         | 10049/100000 [3:09:05<14:36:30,  1.71it/s]
Train steps ... :  10%|█         | 10050/100000 [3:09:05<14:37:27,  1.71it/s]Step... (10050 / 100000 | Loss: 1.3505690097808838, Learning Rate: 9.040201005025126e-05)
+
                                                                             
Step... (10050 / 100000 | Loss: 1.2046982049942017, Learning Rate: 9.040201005025126e-05)
+
Train steps ... :  10%|█         | 10050/100000 [3:09:06<14:37:27,  1.71it/s]
Train steps ... :  10%|█         | 10051/100000 [3:09:06<14:38:18,  1.71it/s]
Train steps ... :  10%|█         | 10052/100000 [3:09:06<14:36:43,  1.71it/s]
Train steps ... :  10%|█         | 10053/100000 [3:09:07<14:36:44,  1.71it/s]
Train steps ... :  10%|█         | 10054/100000 [3:09:08<14:35:40,  1.71it/s]
Train steps ... :  10%|█         | 10055/100000 [3:09:08<14:35:10,  1.71it/s]
Train steps ... :  10%|█         | 10056/100000 [3:09:09<14:35:49,  1.71it/s]
Train steps ... :  10%|█         | 10057/100000 [3:09:09<14:35:12,  1.71it/s]
Train steps ... :  10%|█         | 10058/100000 [3:09:10<14:35:50,  1.71it/s]
Train steps ... :  10%|█         | 10059/100000 [3:09:11<14:35:05,  1.71it/s]
Train steps ... :  10%|█         | 10060/100000 [3:09:11<14:35:12,  1.71it/s]
Train steps ... :  10%|█         | 10061/100000 [3:09:12<14:34:59,  1.71it/s]
Train steps ... :  10%|█         | 10062/100000 [3:09:12<14:34:49,  1.71it/s]
Train steps ... :  10%|█         | 10063/100000 [3:09:13<14:35:03,  1.71it/s]
Train steps ... :  10%|█         | 10064/100000 [3:09:13<14:35:12,  1.71it/s]
Train steps ... :  10%|█         | 10065/100000 [3:09:14<14:34:39,  1.71it/s]
Train steps ... :  10%|█         | 10066/100000 [3:09:15<14:35:02,  1.71it/s]
Train steps ... :  10%|█         | 10067/100000 [3:09:15<14:35:28,  1.71it/s]
Train steps ... :  10%|█         | 10068/100000 [3:09:16<14:35:03,  1.71it/s]
Train steps ... :  10%|█         | 10069/100000 [3:09:16<14:34:33,  1.71it/s]
Train steps ... :  10%|█         | 10070/100000 [3:09:17<14:34:17,  1.71it/s]
Train steps ... :  10%|█         | 10071/100000 [3:09:18<14:34:38,  1.71it/s]
Train steps ... :  10%|█         | 10072/100000 [3:09:18<14:34:28,  1.71it/s]
Train steps ... :  10%|█         | 10073/100000 [3:09:19<14:34:47,  1.71it/s]
Train steps ... :  10%|█         | 10074/100000 [3:09:19<14:34:54,  1.71it/s]
Train steps ... :  10%|█         | 10075/100000 [3:09:20<14:34:49,  1.71it/s]Step... (10075 / 100000 | Loss: 1.5911297798156738, Learning Rate: 9.037688442211056e-05)
+
                                                                             
Step... (10075 / 100000 | Loss: 1.434281349182129, Learning Rate: 9.037688442211056e-05)
+
Train steps ... :  10%|█         | 10075/100000 [3:09:20<14:34:49,  1.71it/s]
Train steps ... :  10%|█         | 10076/100000 [3:09:20<14:35:56,  1.71it/s]
Train steps ... :  10%|█         | 10077/100000 [3:09:21<14:35:54,  1.71it/s]
Train steps ... :  10%|█         | 10078/100000 [3:09:22<14:34:51,  1.71it/s]
Train steps ... :  10%|█         | 10079/100000 [3:09:22<14:34:51,  1.71it/s]
Train steps ... :  10%|█         | 10080/100000 [3:09:23<14:35:44,  1.71it/s]
Train steps ... :  10%|█         | 10081/100000 [3:09:23<14:35:36,  1.71it/s]
Train steps ... :  10%|█         | 10082/100000 [3:09:24<14:35:10,  1.71it/s]
Train steps ... :  10%|█         | 10083/100000 [3:09:25<14:34:40,  1.71it/s]
Train steps ... :  10%|█         | 10084/100000 [3:09:25<14:35:28,  1.71it/s]
Train steps ... :  10%|█         | 10085/100000 [3:09:26<14:35:43,  1.71it/s]
Train steps ... :  10%|█         | 10086/100000 [3:09:26<14:36:18,  1.71it/s]
Train steps ... :  10%|█         | 10087/100000 [3:09:27<14:37:41,  1.71it/s]
Train steps ... :  10%|█         | 10088/100000 [3:09:27<14:37:31,  1.71it/s]
Train steps ... :  10%|█         | 10089/100000 [3:09:28<14:36:32,  1.71it/s]
Train steps ... :  10%|█         | 10090/100000 [3:09:29<14:35:54,  1.71it/s]
Train steps ... :  10%|█         | 10091/100000 [3:09:29<14:36:04,  1.71it/s]
Train steps ... :  10%|█         | 10092/100000 [3:09:30<14:35:22,  1.71it/s]
Train steps ... :  10%|█         | 10093/100000 [3:09:30<14:35:15,  1.71it/s]
Train steps ... :  10%|█         | 10094/100000 [3:09:31<14:35:54,  1.71it/s]
Train steps ... :  10%|█         | 10095/100000 [3:09:32<14:35:22,  1.71it/s]
Train steps ... :  10%|█         | 10096/100000 [3:09:32<14:36:30,  1.71it/s]
Train steps ... :  10%|█         | 10097/100000 [3:09:33<14:36:10,  1.71it/s]
Train steps ... :  10%|█         | 10098/100000 [3:09:33<14:35:30,  1.71it/s]
Train steps ... :  10%|█         | 10099/100000 [3:09:34<14:36:34,  1.71it/s]
Train steps ... :  10%|█         | 10100/100000 [3:09:34<14:35:52,  1.71it/s]Step... (10100 / 100000 | Loss: 1.3467929363250732, Learning Rate: 9.035175879396985e-05)
+
                                                                             
Step... (10100 / 100000 | Loss: 1.2095615863800049, Learning Rate: 9.035175879396985e-05)
+
Train steps ... :  10%|█         | 10100/100000 [3:09:35<14:35:52,  1.71it/s]
Train steps ... :  10%|█         | 10101/100000 [3:09:35<14:36:01,  1.71it/s]
Train steps ... :  10%|█         | 10102/100000 [3:09:36<14:35:39,  1.71it/s]
Train steps ... :  10%|█         | 10103/100000 [3:09:36<14:35:18,  1.71it/s]
Train steps ... :  10%|█         | 10104/100000 [3:09:37<14:35:02,  1.71it/s]
Train steps ... :  10%|█         | 10105/100000 [3:09:37<14:34:44,  1.71it/s]
Train steps ... :  10%|█         | 10106/100000 [3:09:38<14:35:06,  1.71it/s]
Train steps ... :  10%|█         | 10107/100000 [3:09:39<14:35:02,  1.71it/s]
Train steps ... :  10%|█         | 10108/100000 [3:09:39<14:34:48,  1.71it/s]
Train steps ... :  10%|█         | 10109/100000 [3:09:40<14:34:29,  1.71it/s]
Train steps ... :  10%|█         | 10110/100000 [3:09:40<14:33:57,  1.71it/s]
Train steps ... :  10%|█         | 10111/100000 [3:09:41<14:34:40,  1.71it/s]
Train steps ... :  10%|█         | 10112/100000 [3:09:41<14:35:39,  1.71it/s]
Train steps ... :  10%|█         | 10113/100000 [3:09:42<14:35:23,  1.71it/s]
Train steps ... :  10%|█         | 10114/100000 [3:09:43<14:34:39,  1.71it/s]
Train steps ... :  10%|█         | 10115/100000 [3:09:43<14:35:49,  1.71it/s]
Train steps ... :  10%|█         | 10116/100000 [3:09:44<14:36:38,  1.71it/s]
Train steps ... :  10%|█         | 10117/100000 [3:09:44<14:35:48,  1.71it/s]
Train steps ... :  10%|█         | 10118/100000 [3:09:45<14:35:11,  1.71it/s]
Train steps ... :  10%|█         | 10119/100000 [3:09:46<14:34:47,  1.71it/s]
Train steps ... :  10%|█         | 10120/100000 [3:09:46<14:35:18,  1.71it/s]
Train steps ... :  10%|█         | 10121/100000 [3:09:47<14:35:02,  1.71it/s]
Train steps ... :  10%|█         | 10122/100000 [3:09:47<14:34:34,  1.71it/s]
Train steps ... :  10%|█         | 10123/100000 [3:09:48<14:34:25,  1.71it/s]
Train steps ... :  10%|█         | 10124/100000 [3:09:48<14:35:49,  1.71it/s]
Train steps ... :  10%|█         | 10125/100000 [3:09:49<14:35:20,  1.71it/s]Step... (10125 / 100000 | Loss: 1.350957989692688, Learning Rate: 9.032663316582915e-05)
+
                                                                             
Step... (10125 / 100000 | Loss: 1.3610703945159912, Learning Rate: 9.032663316582915e-05)
+
Train steps ... :  10%|█         | 10125/100000 [3:09:49<14:35:20,  1.71it/s]
Train steps ... :  10%|█         | 10126/100000 [3:09:50<14:35:02,  1.71it/s]
Train steps ... :  10%|█         | 10127/100000 [3:09:50<14:34:21,  1.71it/s]
Train steps ... :  10%|█         | 10128/100000 [3:09:51<14:34:29,  1.71it/s]
Train steps ... :  10%|█         | 10129/100000 [3:09:51<14:34:39,  1.71it/s]
Train steps ... :  10%|█         | 10130/100000 [3:09:52<14:34:43,  1.71it/s]
Train steps ... :  10%|█         | 10131/100000 [3:09:53<14:34:49,  1.71it/s]
Train steps ... :  10%|█         | 10132/100000 [3:09:53<14:34:37,  1.71it/s]
Train steps ... :  10%|█         | 10133/100000 [3:09:54<14:34:08,  1.71it/s]
Train steps ... :  10%|█         | 10134/100000 [3:09:54<14:35:06,  1.71it/s]
Train steps ... :  10%|█         | 10135/100000 [3:09:55<14:34:43,  1.71it/s]
Train steps ... :  10%|█         | 10136/100000 [3:09:55<14:34:45,  1.71it/s]
Train steps ... :  10%|█         | 10137/100000 [3:09:56<14:35:35,  1.71it/s]
Train steps ... :  10%|█         | 10138/100000 [3:09:57<14:34:47,  1.71it/s]
Train steps ... :  10%|█         | 10139/100000 [3:09:57<14:35:21,  1.71it/s]
Train steps ... :  10%|█         | 10140/100000 [3:09:58<14:34:36,  1.71it/s]
Train steps ... :  10%|█         | 10141/100000 [3:09:58<14:33:51,  1.71it/s]
Train steps ... :  10%|█         | 10142/100000 [3:09:59<14:34:27,  1.71it/s]
Train steps ... :  10%|█         | 10143/100000 [3:10:00<14:33:55,  1.71it/s]
Train steps ... :  10%|█         | 10144/100000 [3:10:00<14:34:40,  1.71it/s]
Train steps ... :  10%|█         | 10145/100000 [3:10:01<14:34:19,  1.71it/s]
Train steps ... :  10%|█         | 10146/100000 [3:10:01<14:33:38,  1.71it/s]
Train steps ... :  10%|█         | 10147/100000 [3:10:02<14:34:21,  1.71it/s]
Train steps ... :  10%|█         | 10148/100000 [3:10:02<14:34:33,  1.71it/s]
Train steps ... :  10%|█         | 10149/100000 [3:10:03<14:35:36,  1.71it/s]
Train steps ... :  10%|█         | 10150/100000 [3:10:04<14:36:19,  1.71it/s]Step... (10150 / 100000 | Loss: 1.168097734451294, Learning Rate: 9.030150753768845e-05)
+
                                                                             
Step... (10150 / 100000 | Loss: 1.6882219314575195, Learning Rate: 9.030150753768845e-05)
+
Train steps ... :  10%|█         | 10150/100000 [3:10:04<14:36:19,  1.71it/s]
Train steps ... :  10%|█         | 10151/100000 [3:10:04<14:36:24,  1.71it/s]
Train steps ... :  10%|█         | 10152/100000 [3:10:05<14:35:41,  1.71it/s]
Train steps ... :  10%|█         | 10153/100000 [3:10:05<14:35:23,  1.71it/s]
Train steps ... :  10%|█         | 10154/100000 [3:10:06<14:35:02,  1.71it/s]
Train steps ... :  10%|█         | 10155/100000 [3:10:07<14:34:46,  1.71it/s]
Train steps ... :  10%|█         | 10156/100000 [3:10:07<14:34:21,  1.71it/s]
Train steps ... :  10%|█         | 10157/100000 [3:10:08<14:34:15,  1.71it/s]
Train steps ... :  10%|█         | 10158/100000 [3:10:08<14:33:48,  1.71it/s]
Train steps ... :  10%|█         | 10159/100000 [3:10:09<14:35:02,  1.71it/s]
Train steps ... :  10%|█         | 10160/100000 [3:10:10<14:34:12,  1.71it/s]
Train steps ... :  10%|█         | 10161/100000 [3:10:10<14:34:48,  1.71it/s]
Train steps ... :  10%|█         | 10162/100000 [3:10:11<14:36:05,  1.71it/s]
Train steps ... :  10%|█         | 10163/100000 [3:10:11<14:36:50,  1.71it/s]
Train steps ... :  10%|█         | 10164/100000 [3:10:12<14:35:45,  1.71it/s]
Train steps ... :  10%|█         | 10165/100000 [3:10:12<14:35:55,  1.71it/s]
Train steps ... :  10%|█         | 10166/100000 [3:10:13<14:34:50,  1.71it/s]
Train steps ... :  10%|█         | 10167/100000 [3:10:14<14:35:28,  1.71it/s]
Train steps ... :  10%|█         | 10168/100000 [3:10:14<14:34:51,  1.71it/s]
Train steps ... :  10%|█         | 10169/100000 [3:10:15<14:34:49,  1.71it/s]
Train steps ... :  10%|█         | 10170/100000 [3:10:15<14:34:13,  1.71it/s]
Train steps ... :  10%|█         | 10171/100000 [3:10:16<14:34:34,  1.71it/s]
Train steps ... :  10%|█         | 10172/100000 [3:10:17<14:34:11,  1.71it/s]
Train steps ... :  10%|█         | 10173/100000 [3:10:17<14:34:30,  1.71it/s]
Train steps ... :  10%|█         | 10174/100000 [3:10:18<14:35:23,  1.71it/s]
Train steps ... :  10%|█         | 10175/100000 [3:10:18<14:34:20,  1.71it/s]Step... (10175 / 100000 | Loss: 1.0910474061965942, Learning Rate: 9.027638190954774e-05)
+
                                                                             
Step... (10175 / 100000 | Loss: 1.0748200416564941, Learning Rate: 9.027638190954774e-05)
+
Train steps ... :  10%|█         | 10175/100000 [3:10:19<14:34:20,  1.71it/s]
Train steps ... :  10%|█         | 10176/100000 [3:10:19<14:34:47,  1.71it/s]
Train steps ... :  10%|█         | 10177/100000 [3:10:19<14:34:32,  1.71it/s]
Train steps ... :  10%|█         | 10178/100000 [3:10:20<14:34:14,  1.71it/s]
Train steps ... :  10%|█         | 10179/100000 [3:10:21<14:34:20,  1.71it/s]
Train steps ... :  10%|█         | 10180/100000 [3:10:21<14:34:51,  1.71it/s]
Train steps ... :  10%|█         | 10181/100000 [3:10:22<14:34:15,  1.71it/s]
Train steps ... :  10%|█         | 10182/100000 [3:10:22<14:33:39,  1.71it/s]
Train steps ... :  10%|█         | 10183/100000 [3:10:23<14:33:35,  1.71it/s]
Train steps ... :  10%|█         | 10184/100000 [3:10:24<14:34:49,  1.71it/s]
Train steps ... :  10%|█         | 10185/100000 [3:10:24<14:34:43,  1.71it/s]
Train steps ... :  10%|█         | 10186/100000 [3:10:25<14:35:37,  1.71it/s]
Train steps ... :  10%|█         | 10187/100000 [3:10:25<14:34:57,  1.71it/s]
Train steps ... :  10%|█         | 10188/100000 [3:10:26<14:34:22,  1.71it/s]
Train steps ... :  10%|█         | 10189/100000 [3:10:26<14:35:00,  1.71it/s]
Train steps ... :  10%|█         | 10190/100000 [3:10:27<14:35:33,  1.71it/s]
Train steps ... :  10%|█         | 10191/100000 [3:10:28<14:33:26,  1.71it/s]
Train steps ... :  10%|█         | 10192/100000 [3:10:28<14:34:14,  1.71it/s]
Train steps ... :  10%|█         | 10193/100000 [3:10:29<14:35:17,  1.71it/s]
Train steps ... :  10%|█         | 10194/100000 [3:10:29<14:34:48,  1.71it/s]
Train steps ... :  10%|█         | 10195/100000 [3:10:30<14:34:49,  1.71it/s]
Train steps ... :  10%|█         | 10196/100000 [3:10:31<14:34:33,  1.71it/s]
Train steps ... :  10%|█         | 10197/100000 [3:10:31<14:35:11,  1.71it/s]
Train steps ... :  10%|█         | 10198/100000 [3:10:32<14:35:45,  1.71it/s]
Train steps ... :  10%|█         | 10199/100000 [3:10:32<14:36:15,  1.71it/s]
Train steps ... :  10%|█         | 10200/100000 [3:10:33<14:35:27,  1.71it/s]Step... (10200 / 100000 | Loss: 1.105616569519043, Learning Rate: 9.025125628140704e-05)
+
                                                                             
Step... (10200 / 100000 | Loss: 1.0745769739151, Learning Rate: 9.025125628140704e-05)
+
Train steps ... :  10%|█         | 10200/100000 [3:10:33<14:35:27,  1.71it/s]
Train steps ... :  10%|█         | 10201/100000 [3:10:33<14:37:13,  1.71it/s]
Train steps ... :  10%|█         | 10202/100000 [3:10:34<14:37:54,  1.70it/s]
Train steps ... :  10%|█         | 10203/100000 [3:10:35<14:35:16,  1.71it/s]
Train steps ... :  10%|█         | 10204/100000 [3:10:35<14:34:36,  1.71it/s]
Train steps ... :  10%|█         | 10205/100000 [3:10:36<14:35:03,  1.71it/s]
Train steps ... :  10%|█         | 10206/100000 [3:10:36<14:34:56,  1.71it/s]
Train steps ... :  10%|█         | 10207/100000 [3:10:37<14:34:02,  1.71it/s]
Train steps ... :  10%|█         | 10208/100000 [3:10:38<14:36:02,  1.71it/s]
Train steps ... :  10%|█         | 10209/100000 [3:10:38<14:36:01,  1.71it/s]
Train steps ... :  10%|█         | 10210/100000 [3:10:39<14:36:02,  1.71it/s]
Train steps ... :  10%|█         | 10211/100000 [3:10:39<14:34:07,  1.71it/s]
Train steps ... :  10%|█         | 10212/100000 [3:10:40<14:33:43,  1.71it/s]
Train steps ... :  10%|█         | 10213/100000 [3:10:40<14:33:55,  1.71it/s]
Train steps ... :  10%|█         | 10214/100000 [3:10:41<14:33:16,  1.71it/s]
Train steps ... :  10%|█         | 10215/100000 [3:10:42<14:34:46,  1.71it/s]
Train steps ... :  10%|█         | 10216/100000 [3:10:42<14:33:49,  1.71it/s]
Train steps ... :  10%|█         | 10217/100000 [3:10:43<14:34:53,  1.71it/s]
Train steps ... :  10%|█         | 10218/100000 [3:10:43<14:34:06,  1.71it/s]
Train steps ... :  10%|█         | 10219/100000 [3:10:44<14:34:08,  1.71it/s]
Train steps ... :  10%|█         | 10220/100000 [3:10:45<14:34:06,  1.71it/s]
Train steps ... :  10%|█         | 10221/100000 [3:10:45<14:34:04,  1.71it/s]
Train steps ... :  10%|█         | 10222/100000 [3:10:46<14:35:40,  1.71it/s]
Train steps ... :  10%|█         | 10223/100000 [3:10:46<14:35:21,  1.71it/s]
Train steps ... :  10%|█         | 10224/100000 [3:10:47<14:36:39,  1.71it/s]
Train steps ... :  10%|█         | 10225/100000 [3:10:48<14:35:39,  1.71it/s]Step... (10225 / 100000 | Loss: 1.2427947521209717, Learning Rate: 9.022613065326634e-05)
+
                                                                             
Step... (10225 / 100000 | Loss: 1.446066975593567, Learning Rate: 9.022613065326634e-05)
+
Train steps ... :  10%|█         | 10225/100000 [3:10:48<14:35:39,  1.71it/s]
Train steps ... :  10%|█         | 10226/100000 [3:10:48<14:35:37,  1.71it/s]
Train steps ... :  10%|█         | 10227/100000 [3:10:49<14:34:32,  1.71it/s]
Train steps ... :  10%|█         | 10228/100000 [3:10:49<14:34:07,  1.71it/s]
Train steps ... :  10%|█         | 10229/100000 [3:10:50<14:33:28,  1.71it/s]
Train steps ... :  10%|█         | 10230/100000 [3:10:50<14:34:33,  1.71it/s]
Train steps ... :  10%|█         | 10231/100000 [3:10:51<14:33:56,  1.71it/s]
Train steps ... :  10%|█         | 10232/100000 [3:10:52<14:33:28,  1.71it/s]
Train steps ... :  10%|█         | 10233/100000 [3:10:52<14:34:42,  1.71it/s]
Train steps ... :  10%|█         | 10234/100000 [3:10:53<14:34:57,  1.71it/s]
Train steps ... :  10%|█         | 10235/100000 [3:10:53<14:34:09,  1.71it/s]
Train steps ... :  10%|█         | 10236/100000 [3:10:54<14:33:45,  1.71it/s]
Train steps ... :  10%|█         | 10237/100000 [3:10:55<14:34:10,  1.71it/s]
Train steps ... :  10%|█         | 10238/100000 [3:10:55<14:33:42,  1.71it/s]
Train steps ... :  10%|█         | 10239/100000 [3:10:56<14:33:35,  1.71it/s]
Train steps ... :  10%|█         | 10240/100000 [3:10:56<14:34:18,  1.71it/s]
Train steps ... :  10%|█         | 10241/100000 [3:10:57<14:35:06,  1.71it/s]
Train steps ... :  10%|█         | 10242/100000 [3:10:57<14:35:45,  1.71it/s]
Train steps ... :  10%|█         | 10243/100000 [3:10:58<14:34:28,  1.71it/s]
Train steps ... :  10%|█         | 10244/100000 [3:10:59<14:34:36,  1.71it/s]
Train steps ... :  10%|█         | 10245/100000 [3:10:59<14:34:57,  1.71it/s]
Train steps ... :  10%|█         | 10246/100000 [3:11:00<14:35:00,  1.71it/s]
Train steps ... :  10%|█         | 10247/100000 [3:11:00<14:34:31,  1.71it/s]
Train steps ... :  10%|█         | 10248/100000 [3:11:01<14:33:52,  1.71it/s]
Train steps ... :  10%|█         | 10249/100000 [3:11:02<14:33:10,  1.71it/s]
Train steps ... :  10%|█         | 10250/100000 [3:11:02<14:33:19,  1.71it/s]Step... (10250 / 100000 | Loss: 1.13421630859375, Learning Rate: 9.020100502512563e-05)
+
                                                                             
Step... (10250 / 100000 | Loss: 0.9447852373123169, Learning Rate: 9.020100502512563e-05)
+
Train steps ... :  10%|█         | 10250/100000 [3:11:02<14:33:19,  1.71it/s]
Train steps ... :  10%|█         | 10251/100000 [3:11:03<14:33:33,  1.71it/s]
Train steps ... :  10%|█         | 10252/100000 [3:11:03<14:33:38,  1.71it/s]
Train steps ... :  10%|█         | 10253/100000 [3:11:04<14:34:21,  1.71it/s]
Train steps ... :  10%|█         | 10254/100000 [3:11:04<14:34:59,  1.71it/s]
Train steps ... :  10%|█         | 10255/100000 [3:11:05<14:35:10,  1.71it/s]
Train steps ... :  10%|█         | 10256/100000 [3:11:06<14:33:58,  1.71it/s]
Train steps ... :  10%|█         | 10257/100000 [3:11:06<14:33:50,  1.71it/s]
Train steps ... :  10%|█         | 10258/100000 [3:11:07<14:33:53,  1.71it/s]
Train steps ... :  10%|█         | 10259/100000 [3:11:07<14:34:54,  1.71it/s]
Train steps ... :  10%|█         | 10260/100000 [3:11:08<14:35:19,  1.71it/s]
Train steps ... :  10%|█         | 10261/100000 [3:11:09<14:34:25,  1.71it/s]
Train steps ... :  10%|█         | 10262/100000 [3:11:09<14:34:18,  1.71it/s]
Train steps ... :  10%|█         | 10263/100000 [3:11:10<14:33:42,  1.71it/s]
Train steps ... :  10%|█         | 10264/100000 [3:11:10<14:34:44,  1.71it/s]
Train steps ... :  10%|█         | 10265/100000 [3:11:11<14:34:55,  1.71it/s]
Train steps ... :  10%|█         | 10266/100000 [3:11:11<14:34:26,  1.71it/s]
Train steps ... :  10%|█         | 10267/100000 [3:11:12<14:34:46,  1.71it/s]
Train steps ... :  10%|█         | 10268/100000 [3:11:13<14:34:06,  1.71it/s]
Train steps ... :  10%|█         | 10269/100000 [3:11:13<14:34:06,  1.71it/s]
Train steps ... :  10%|█         | 10270/100000 [3:11:14<14:34:58,  1.71it/s]
Train steps ... :  10%|█         | 10271/100000 [3:11:14<14:34:17,  1.71it/s]
Train steps ... :  10%|█         | 10272/100000 [3:11:15<14:33:42,  1.71it/s]
Train steps ... :  10%|█         | 10273/100000 [3:11:16<14:34:56,  1.71it/s]
Train steps ... :  10%|█         | 10274/100000 [3:11:16<14:34:25,  1.71it/s]
Train steps ... :  10%|█         | 10275/100000 [3:11:17<14:34:57,  1.71it/s]Step... (10275 / 100000 | Loss: 1.1475878953933716, Learning Rate: 9.017587939698493e-05)
+
                                                                             
Step... (10275 / 100000 | Loss: 1.0554271936416626, Learning Rate: 9.017587939698493e-05)
+
Train steps ... :  10%|█         | 10275/100000 [3:11:17<14:34:57,  1.71it/s]
Train steps ... :  10%|█         | 10276/100000 [3:11:17<14:35:21,  1.71it/s]
Train steps ... :  10%|█         | 10277/100000 [3:11:18<14:34:52,  1.71it/s]
Train steps ... :  10%|█         | 10278/100000 [3:11:18<14:34:00,  1.71it/s]
Train steps ... :  10%|█         | 10279/100000 [3:11:19<14:34:11,  1.71it/s]
Train steps ... :  10%|█         | 10280/100000 [3:11:20<14:34:48,  1.71it/s]
Train steps ... :  10%|█         | 10281/100000 [3:11:20<14:34:22,  1.71it/s]
Train steps ... :  10%|█         | 10282/100000 [3:11:21<14:33:59,  1.71it/s]
Train steps ... :  10%|█         | 10283/100000 [3:11:21<14:34:06,  1.71it/s]
Train steps ... :  10%|█         | 10284/100000 [3:11:22<14:33:55,  1.71it/s]
Train steps ... :  10%|█         | 10285/100000 [3:11:23<14:33:18,  1.71it/s]
Train steps ... :  10%|█         | 10286/100000 [3:11:23<14:34:34,  1.71it/s]
Train steps ... :  10%|█         | 10287/100000 [3:11:24<14:33:52,  1.71it/s]
Train steps ... :  10%|█         | 10288/100000 [3:11:24<14:33:23,  1.71it/s]
Train steps ... :  10%|█         | 10289/100000 [3:11:25<14:34:08,  1.71it/s]
Train steps ... :  10%|█         | 10290/100000 [3:11:25<14:33:27,  1.71it/s]
Train steps ... :  10%|█         | 10291/100000 [3:11:26<14:33:43,  1.71it/s]
Train steps ... :  10%|█         | 10292/100000 [3:11:27<14:34:00,  1.71it/s]
Train steps ... :  10%|█         | 10293/100000 [3:11:27<14:33:42,  1.71it/s]
Train steps ... :  10%|█         | 10294/100000 [3:11:28<14:34:15,  1.71it/s]
Train steps ... :  10%|█         | 10295/100000 [3:11:28<14:33:21,  1.71it/s]
Train steps ... :  10%|█         | 10296/100000 [3:11:29<14:33:18,  1.71it/s]
Train steps ... :  10%|█         | 10297/100000 [3:11:30<14:32:42,  1.71it/s]
Train steps ... :  10%|█         | 10298/100000 [3:11:30<14:33:04,  1.71it/s]
Train steps ... :  10%|█         | 10299/100000 [3:11:31<14:33:12,  1.71it/s]
Train steps ... :  10%|█         | 10300/100000 [3:11:31<14:33:16,  1.71it/s]Step... (10300 / 100000 | Loss: 1.236466407775879, Learning Rate: 9.015075376884423e-05)
+
                                                                             
Step... (10300 / 100000 | Loss: 1.2616581916809082, Learning Rate: 9.015075376884423e-05)
+
Train steps ... :  10%|█         | 10300/100000 [3:11:32<14:33:16,  1.71it/s]
Train steps ... :  10%|█         | 10301/100000 [3:11:32<14:33:14,  1.71it/s]
Train steps ... :  10%|█         | 10302/100000 [3:11:33<14:33:06,  1.71it/s]
Train steps ... :  10%|█         | 10303/100000 [3:11:33<14:33:19,  1.71it/s]
Train steps ... :  10%|█         | 10304/100000 [3:11:34<14:33:25,  1.71it/s]
Train steps ... :  10%|█         | 10305/100000 [3:11:34<14:34:06,  1.71it/s]
Train steps ... :  10%|█         | 10306/100000 [3:11:35<14:33:19,  1.71it/s]
Train steps ... :  10%|█         | 10307/100000 [3:11:35<14:33:13,  1.71it/s]
Train steps ... :  10%|█         | 10308/100000 [3:11:36<14:33:05,  1.71it/s]
Train steps ... :  10%|█         | 10309/100000 [3:11:37<14:32:58,  1.71it/s]
Train steps ... :  10%|█         | 10310/100000 [3:11:37<14:33:11,  1.71it/s]
Train steps ... :  10%|█         | 10311/100000 [3:11:38<14:32:43,  1.71it/s]
Train steps ... :  10%|█         | 10312/100000 [3:11:38<14:32:44,  1.71it/s]
Train steps ... :  10%|█         | 10313/100000 [3:11:39<14:33:24,  1.71it/s]
Train steps ... :  10%|█         | 10314/100000 [3:11:40<14:33:39,  1.71it/s]
Train steps ... :  10%|█         | 10315/100000 [3:11:40<14:34:01,  1.71it/s]
Train steps ... :  10%|█         | 10316/100000 [3:11:41<14:34:07,  1.71it/s]
Train steps ... :  10%|█         | 10317/100000 [3:11:41<14:34:59,  1.71it/s]
Train steps ... :  10%|█         | 10318/100000 [3:11:42<14:34:24,  1.71it/s]
Train steps ... :  10%|█         | 10319/100000 [3:11:42<14:33:23,  1.71it/s]
Train steps ... :  10%|█         | 10320/100000 [3:11:43<14:34:37,  1.71it/s]
Train steps ... :  10%|█         | 10321/100000 [3:11:44<14:33:41,  1.71it/s]
Train steps ... :  10%|█         | 10322/100000 [3:11:44<14:33:31,  1.71it/s]
Train steps ... :  10%|█         | 10323/100000 [3:11:45<14:33:10,  1.71it/s]
Train steps ... :  10%|█         | 10324/100000 [3:11:45<14:33:25,  1.71it/s]
Train steps ... :  10%|█         | 10325/100000 [3:11:46<14:33:43,  1.71it/s]Step... (10325 / 100000 | Loss: 1.8826658725738525, Learning Rate: 9.012562814070352e-05)
+
                                                                             
Step... (10325 / 100000 | Loss: 1.6703765392303467, Learning Rate: 9.012562814070352e-05)
+
Train steps ... :  10%|█         | 10325/100000 [3:11:46<14:33:43,  1.71it/s]
Train steps ... :  10%|█         | 10326/100000 [3:11:47<14:33:23,  1.71it/s]
Train steps ... :  10%|█         | 10327/100000 [3:11:47<14:32:46,  1.71it/s]
Train steps ... :  10%|█         | 10328/100000 [3:11:48<14:33:14,  1.71it/s]
Train steps ... :  10%|█         | 10329/100000 [3:11:48<14:33:27,  1.71it/s]
Train steps ... :  10%|█         | 10330/100000 [3:11:49<14:33:18,  1.71it/s]
Train steps ... :  10%|█         | 10331/100000 [3:11:49<14:33:23,  1.71it/s]
Train steps ... :  10%|█         | 10332/100000 [3:11:50<14:33:36,  1.71it/s]
Train steps ... :  10%|█         | 10333/100000 [3:11:51<14:32:46,  1.71it/s]
Train steps ... :  10%|█         | 10334/100000 [3:11:51<14:32:49,  1.71it/s]
Train steps ... :  10%|█         | 10335/100000 [3:11:52<14:33:57,  1.71it/s]
Train steps ... :  10%|█         | 10336/100000 [3:11:52<14:33:34,  1.71it/s]
Train steps ... :  10%|█         | 10337/100000 [3:11:53<14:34:02,  1.71it/s]
Train steps ... :  10%|█         | 10338/100000 [3:11:54<14:33:20,  1.71it/s]
Train steps ... :  10%|█         | 10339/100000 [3:11:54<14:33:08,  1.71it/s]
Train steps ... :  10%|█         | 10340/100000 [3:11:55<14:33:47,  1.71it/s]
Train steps ... :  10%|█         | 10341/100000 [3:11:55<14:33:33,  1.71it/s]
Train steps ... :  10%|█         | 10342/100000 [3:11:56<14:34:32,  1.71it/s]
Train steps ... :  10%|█         | 10343/100000 [3:11:56<14:33:36,  1.71it/s]
Train steps ... :  10%|█         | 10344/100000 [3:11:57<14:33:09,  1.71it/s]
Train steps ... :  10%|█         | 10345/100000 [3:11:58<14:33:47,  1.71it/s]
Train steps ... :  10%|█         | 10346/100000 [3:11:58<14:33:20,  1.71it/s]
Train steps ... :  10%|█         | 10347/100000 [3:11:59<14:35:15,  1.71it/s]
Train steps ... :  10%|█         | 10348/100000 [3:11:59<14:35:34,  1.71it/s]
Train steps ... :  10%|█         | 10349/100000 [3:12:00<14:34:20,  1.71it/s]
Train steps ... :  10%|█         | 10350/100000 [3:12:01<14:34:49,  1.71it/s]Step... (10350 / 100000 | Loss: 1.354914665222168, Learning Rate: 9.010050251256282e-05)
+
                                                                             
Step... (10350 / 100000 | Loss: 1.2448198795318604, Learning Rate: 9.010050251256282e-05)
+
Train steps ... :  10%|█         | 10350/100000 [3:12:01<14:34:49,  1.71it/s]
Train steps ... :  10%|█         | 10351/100000 [3:12:01<14:34:24,  1.71it/s]
Train steps ... :  10%|█         | 10352/100000 [3:12:02<14:33:27,  1.71it/s]
Train steps ... :  10%|█         | 10353/100000 [3:12:02<14:33:24,  1.71it/s]
Train steps ... :  10%|█         | 10354/100000 [3:12:03<14:32:45,  1.71it/s]
Train steps ... :  10%|█         | 10355/100000 [3:12:03<14:32:54,  1.71it/s]
Train steps ... :  10%|█         | 10356/100000 [3:12:04<14:33:29,  1.71it/s]
Train steps ... :  10%|█         | 10357/100000 [3:12:05<14:32:55,  1.71it/s]
Train steps ... :  10%|█         | 10358/100000 [3:12:05<14:33:02,  1.71it/s]
Train steps ... :  10%|█         | 10359/100000 [3:12:06<14:33:01,  1.71it/s]
Train steps ... :  10%|█         | 10360/100000 [3:12:06<14:32:41,  1.71it/s]
Train steps ... :  10%|█         | 10361/100000 [3:12:07<14:33:12,  1.71it/s]
Train steps ... :  10%|█         | 10362/100000 [3:12:08<14:32:52,  1.71it/s]
Train steps ... :  10%|█         | 10363/100000 [3:12:08<14:33:04,  1.71it/s]
Train steps ... :  10%|█         | 10364/100000 [3:12:09<14:32:31,  1.71it/s]
Train steps ... :  10%|█         | 10365/100000 [3:12:09<14:33:08,  1.71it/s]
Train steps ... :  10%|█         | 10366/100000 [3:12:10<14:32:47,  1.71it/s]
Train steps ... :  10%|█         | 10367/100000 [3:12:10<14:32:12,  1.71it/s]
Train steps ... :  10%|█         | 10368/100000 [3:12:11<14:32:47,  1.71it/s]
Train steps ... :  10%|█         | 10369/100000 [3:12:12<14:32:46,  1.71it/s]
Train steps ... :  10%|█         | 10370/100000 [3:12:12<14:32:45,  1.71it/s]
Train steps ... :  10%|█         | 10371/100000 [3:12:13<14:33:23,  1.71it/s]
Train steps ... :  10%|█         | 10372/100000 [3:12:13<14:33:10,  1.71it/s]
Train steps ... :  10%|█         | 10373/100000 [3:12:14<14:33:00,  1.71it/s]
Train steps ... :  10%|█         | 10374/100000 [3:12:15<14:32:41,  1.71it/s]
Train steps ... :  10%|█         | 10375/100000 [3:12:15<14:32:56,  1.71it/s]Step... (10375 / 100000 | Loss: 1.4943276643753052, Learning Rate: 9.007537688442212e-05)
+
                                                                             
Step... (10375 / 100000 | Loss: 1.1599198579788208, Learning Rate: 9.007537688442212e-05)
+
Train steps ... :  10%|█         | 10375/100000 [3:12:16<14:32:56,  1.71it/s]
Train steps ... :  10%|█         | 10376/100000 [3:12:16<14:32:53,  1.71it/s]
Train steps ... :  10%|█         | 10377/100000 [3:12:16<14:33:19,  1.71it/s]
Train steps ... :  10%|█         | 10378/100000 [3:12:17<14:33:37,  1.71it/s]
Train steps ... :  10%|█         | 10379/100000 [3:12:18<14:32:55,  1.71it/s]
Train steps ... :  10%|█         | 10380/100000 [3:12:18<14:32:44,  1.71it/s]
Train steps ... :  10%|█         | 10381/100000 [3:12:19<14:32:32,  1.71it/s]
Train steps ... :  10%|█         | 10382/100000 [3:12:19<14:33:02,  1.71it/s]
Train steps ... :  10%|█         | 10383/100000 [3:12:20<14:32:57,  1.71it/s]
Train steps ... :  10%|█         | 10384/100000 [3:12:20<14:32:27,  1.71it/s]
Train steps ... :  10%|█         | 10385/100000 [3:12:21<14:33:12,  1.71it/s]
Train steps ... :  10%|█         | 10386/100000 [3:12:22<14:32:44,  1.71it/s]
Train steps ... :  10%|█         | 10387/100000 [3:12:22<14:33:04,  1.71it/s]
Train steps ... :  10%|█         | 10388/100000 [3:12:23<14:33:09,  1.71it/s]
Train steps ... :  10%|█         | 10389/100000 [3:12:23<14:33:47,  1.71it/s]
Train steps ... :  10%|█         | 10390/100000 [3:12:24<14:33:24,  1.71it/s]
Train steps ... :  10%|█         | 10391/100000 [3:12:25<14:33:52,  1.71it/s]
Train steps ... :  10%|█         | 10392/100000 [3:12:25<14:34:48,  1.71it/s]
Train steps ... :  10%|█         | 10393/100000 [3:12:26<14:33:48,  1.71it/s]
Train steps ... :  10%|█         | 10394/100000 [3:12:26<14:33:22,  1.71it/s]
Train steps ... :  10%|█         | 10395/100000 [3:12:27<14:33:49,  1.71it/s]
Train steps ... :  10%|█         | 10396/100000 [3:12:27<14:33:07,  1.71it/s]
Train steps ... :  10%|█         | 10397/100000 [3:12:28<14:32:50,  1.71it/s]
Train steps ... :  10%|█         | 10398/100000 [3:12:29<14:32:57,  1.71it/s]
Train steps ... :  10%|█         | 10399/100000 [3:12:29<14:33:46,  1.71it/s]
Train steps ... :  10%|█         | 10400/100000 [3:12:30<14:32:30,  1.71it/s]Step... (10400 / 100000 | Loss: 1.397573709487915, Learning Rate: 9.005025125628141e-05)
+
                                                                             
Step... (10400 / 100000 | Loss: 1.3085224628448486, Learning Rate: 9.005025125628141e-05)
+
Train steps ... :  10%|█         | 10400/100000 [3:12:30<14:32:30,  1.71it/s]
Train steps ... :  10%|█         | 10401/100000 [3:12:30<14:33:41,  1.71it/s]
Train steps ... :  10%|█         | 10402/100000 [3:12:31<14:32:46,  1.71it/s]
Train steps ... :  10%|█         | 10403/100000 [3:12:32<14:32:30,  1.71it/s]
Train steps ... :  10%|█         | 10404/100000 [3:12:32<14:32:58,  1.71it/s]
Train steps ... :  10%|█         | 10405/100000 [3:12:33<14:34:06,  1.71it/s]
Train steps ... :  10%|█         | 10406/100000 [3:12:33<14:33:04,  1.71it/s]
Train steps ... :  10%|█         | 10407/100000 [3:12:34<14:32:56,  1.71it/s]
Train steps ... :  10%|█         | 10408/100000 [3:12:34<14:33:22,  1.71it/s]
Train steps ... :  10%|█         | 10409/100000 [3:12:35<14:33:51,  1.71it/s]
Train steps ... :  10%|█         | 10410/100000 [3:12:36<14:33:55,  1.71it/s]
Train steps ... :  10%|█         | 10411/100000 [3:12:36<14:32:47,  1.71it/s]
Train steps ... :  10%|█         | 10412/100000 [3:12:37<14:32:47,  1.71it/s]
Train steps ... :  10%|█         | 10413/100000 [3:12:37<14:32:34,  1.71it/s]
Train steps ... :  10%|█         | 10414/100000 [3:12:38<14:32:25,  1.71it/s]
Train steps ... :  10%|█         | 10415/100000 [3:12:39<14:33:03,  1.71it/s]
Train steps ... :  10%|█         | 10416/100000 [3:12:39<14:32:27,  1.71it/s]
Train steps ... :  10%|█         | 10417/100000 [3:12:40<14:32:19,  1.71it/s]
Train steps ... :  10%|█         | 10418/100000 [3:12:40<14:31:38,  1.71it/s]
Train steps ... :  10%|█         | 10419/100000 [3:12:41<14:32:25,  1.71it/s]
Train steps ... :  10%|█         | 10420/100000 [3:12:41<14:32:22,  1.71it/s]
Train steps ... :  10%|█         | 10421/100000 [3:12:42<14:32:18,  1.71it/s]
Train steps ... :  10%|█         | 10422/100000 [3:12:43<14:32:58,  1.71it/s]
Train steps ... :  10%|█         | 10423/100000 [3:12:43<14:33:35,  1.71it/s]
Train steps ... :  10%|█         | 10424/100000 [3:12:44<14:32:30,  1.71it/s]
Train steps ... :  10%|█         | 10425/100000 [3:12:44<14:34:08,  1.71it/s]Step... (10425 / 100000 | Loss: 1.1660869121551514, Learning Rate: 9.002512562814071e-05)
+
                                                                             
Step... (10425 / 100000 | Loss: 1.6536953449249268, Learning Rate: 9.002512562814071e-05)
+
Train steps ... :  10%|█         | 10425/100000 [3:12:45<14:34:08,  1.71it/s]
Train steps ... :  10%|█         | 10426/100000 [3:12:45<14:34:29,  1.71it/s]
Train steps ... :  10%|█         | 10427/100000 [3:12:46<14:33:44,  1.71it/s]
Train steps ... :  10%|█         | 10428/100000 [3:12:46<14:34:06,  1.71it/s]
Train steps ... :  10%|█         | 10429/100000 [3:12:47<14:33:07,  1.71it/s]
Train steps ... :  10%|█         | 10430/100000 [3:12:47<14:32:38,  1.71it/s]
Train steps ... :  10%|█         | 10431/100000 [3:12:48<14:32:19,  1.71it/s]
Train steps ... :  10%|█         | 10432/100000 [3:12:49<14:32:33,  1.71it/s]
Train steps ... :  10%|█         | 10433/100000 [3:12:49<14:32:14,  1.71it/s]
Train steps ... :  10%|█         | 10434/100000 [3:12:50<14:33:05,  1.71it/s]
Train steps ... :  10%|█         | 10435/100000 [3:12:50<14:32:39,  1.71it/s]
Train steps ... :  10%|█         | 10436/100000 [3:12:51<14:32:18,  1.71it/s]
Train steps ... :  10%|█         | 10437/100000 [3:12:51<14:32:08,  1.71it/s]
Train steps ... :  10%|█         | 10438/100000 [3:12:52<14:33:56,  1.71it/s]
Train steps ... :  10%|█         | 10439/100000 [3:12:53<14:33:28,  1.71it/s]
Train steps ... :  10%|█         | 10440/100000 [3:12:53<14:33:09,  1.71it/s]
Train steps ... :  10%|█         | 10441/100000 [3:12:54<14:33:48,  1.71it/s]
Train steps ... :  10%|█         | 10442/100000 [3:12:54<14:33:31,  1.71it/s]
Train steps ... :  10%|█         | 10443/100000 [3:12:55<14:33:30,  1.71it/s]
Train steps ... :  10%|█         | 10444/100000 [3:12:56<14:33:04,  1.71it/s]
Train steps ... :  10%|█         | 10445/100000 [3:12:56<14:32:48,  1.71it/s]
Train steps ... :  10%|█         | 10446/100000 [3:12:57<14:33:06,  1.71it/s]
Train steps ... :  10%|█         | 10447/100000 [3:12:57<14:33:58,  1.71it/s]
Train steps ... :  10%|█         | 10448/100000 [3:12:58<14:33:13,  1.71it/s]
Train steps ... :  10%|█         | 10449/100000 [3:12:58<14:32:42,  1.71it/s]
Train steps ... :  10%|█         | 10450/100000 [3:12:59<14:31:56,  1.71it/s]Step... (10450 / 100000 | Loss: 1.1035233736038208, Learning Rate: 9e-05)
+
                                                                             
Step... (10450 / 100000 | Loss: 1.011134147644043, Learning Rate: 9e-05)
+
Train steps ... :  10%|█         | 10450/100000 [3:12:59<14:31:56,  1.71it/s]
Train steps ... :  10%|█         | 10451/100000 [3:13:00<14:32:00,  1.71it/s]
Train steps ... :  10%|█         | 10452/100000 [3:13:00<14:32:09,  1.71it/s]
Train steps ... :  10%|█         | 10453/100000 [3:13:01<14:32:27,  1.71it/s]
Train steps ... :  10%|█         | 10454/100000 [3:13:01<14:32:13,  1.71it/s]
Train steps ... :  10%|█         | 10455/100000 [3:13:02<14:31:42,  1.71it/s]
Train steps ... :  10%|█         | 10456/100000 [3:13:03<14:32:00,  1.71it/s]
Train steps ... :  10%|█         | 10457/100000 [3:13:03<14:31:28,  1.71it/s]
Train steps ... :  10%|█         | 10458/100000 [3:13:04<14:31:02,  1.71it/s]
Train steps ... :  10%|█         | 10459/100000 [3:13:04<14:30:50,  1.71it/s]
Train steps ... :  10%|█         | 10460/100000 [3:13:05<14:31:05,  1.71it/s]
Train steps ... :  10%|█         | 10461/100000 [3:13:05<14:31:28,  1.71it/s]
Train steps ... :  10%|█         | 10462/100000 [3:13:06<14:31:30,  1.71it/s]
Train steps ... :  10%|█         | 10463/100000 [3:13:07<14:31:48,  1.71it/s]
Train steps ... :  10%|█         | 10464/100000 [3:13:07<14:31:37,  1.71it/s]
Train steps ... :  10%|█         | 10465/100000 [3:13:08<14:32:33,  1.71it/s]
Train steps ... :  10%|█         | 10466/100000 [3:13:08<14:32:19,  1.71it/s]
Train steps ... :  10%|█         | 10467/100000 [3:13:09<14:32:26,  1.71it/s]
Train steps ... :  10%|█         | 10468/100000 [3:13:10<14:32:15,  1.71it/s]
Train steps ... :  10%|█         | 10469/100000 [3:13:10<14:31:33,  1.71it/s]
Train steps ... :  10%|█         | 10470/100000 [3:13:11<14:32:18,  1.71it/s]
Train steps ... :  10%|█         | 10471/100000 [3:13:11<14:31:11,  1.71it/s]
Train steps ... :  10%|█         | 10472/100000 [3:13:12<14:31:47,  1.71it/s]
Train steps ... :  10%|█         | 10473/100000 [3:13:12<14:32:40,  1.71it/s]
Train steps ... :  10%|█         | 10474/100000 [3:13:13<14:32:34,  1.71it/s]
Train steps ... :  10%|█         | 10475/100000 [3:13:14<14:31:57,  1.71it/s]Step... (10475 / 100000 | Loss: 1.2519837617874146, Learning Rate: 8.99748743718593e-05)
+
                                                                             
Step... (10475 / 100000 | Loss: 1.1928155422210693, Learning Rate: 8.99748743718593e-05)
+
Train steps ... :  10%|█         | 10475/100000 [3:13:14<14:31:57,  1.71it/s]
Train steps ... :  10%|█         | 10476/100000 [3:13:14<14:32:52,  1.71it/s]
Train steps ... :  10%|█         | 10477/100000 [3:13:15<14:32:24,  1.71it/s]
Train steps ... :  10%|█         | 10478/100000 [3:13:15<14:32:12,  1.71it/s]
Train steps ... :  10%|█         | 10479/100000 [3:13:16<14:32:59,  1.71it/s]
Train steps ... :  10%|█         | 10480/100000 [3:13:17<14:32:08,  1.71it/s]
Train steps ... :  10%|█         | 10481/100000 [3:13:17<14:31:39,  1.71it/s]
Train steps ... :  10%|█         | 10482/100000 [3:13:18<14:31:26,  1.71it/s]
Train steps ... :  10%|█         | 10483/100000 [3:13:18<14:32:10,  1.71it/s]
Train steps ... :  10%|█         | 10484/100000 [3:13:19<14:31:51,  1.71it/s]
Train steps ... :  10%|█         | 10485/100000 [3:13:19<14:31:45,  1.71it/s]
Train steps ... :  10%|█         | 10486/100000 [3:13:20<14:32:52,  1.71it/s]
Train steps ... :  10%|█         | 10487/100000 [3:13:21<14:33:41,  1.71it/s]
Train steps ... :  10%|█         | 10488/100000 [3:13:21<14:33:10,  1.71it/s]
Train steps ... :  10%|█         | 10489/100000 [3:13:22<14:32:26,  1.71it/s]
Train steps ... :  10%|█         | 10490/100000 [3:13:22<14:32:11,  1.71it/s]
Train steps ... :  10%|█         | 10491/100000 [3:13:23<14:31:38,  1.71it/s]
Train steps ... :  10%|█         | 10492/100000 [3:13:24<14:31:32,  1.71it/s]
Train steps ... :  10%|█         | 10493/100000 [3:13:24<14:31:49,  1.71it/s]
Train steps ... :  10%|█         | 10494/100000 [3:13:25<14:31:29,  1.71it/s]
Train steps ... :  10%|█         | 10495/100000 [3:13:25<14:31:10,  1.71it/s]
Train steps ... :  10%|█         | 10496/100000 [3:13:26<14:31:05,  1.71it/s]
Train steps ... :  10%|█         | 10497/100000 [3:13:26<14:31:58,  1.71it/s]
Train steps ... :  10%|█         | 10498/100000 [3:13:27<14:31:14,  1.71it/s]
Train steps ... :  10%|█         | 10499/100000 [3:13:28<14:30:56,  1.71it/s]
Train steps ... :  10%|█         | 10500/100000 [3:13:28<14:31:06,  1.71it/s]Step... (10500 / 100000 | Loss: 1.308274745941162, Learning Rate: 8.99497487437186e-05)
+
                                                                             
Step... (10500 / 100000 | Loss: 1.1188833713531494, Learning Rate: 8.99497487437186e-05)
+
Train steps ... :  10%|█         | 10500/100000 [3:13:29<14:31:06,  1.71it/s]
Train steps ... :  11%|█         | 10501/100000 [3:13:29<14:31:33,  1.71it/s]
Train steps ... :  11%|█         | 10502/100000 [3:13:29<14:31:42,  1.71it/s]
Train steps ... :  11%|█         | 10503/100000 [3:13:30<14:31:16,  1.71it/s]
Train steps ... :  11%|█         | 10504/100000 [3:13:31<14:31:18,  1.71it/s]
Train steps ... :  11%|█         | 10505/100000 [3:13:31<14:31:25,  1.71it/s]
Train steps ... :  11%|█         | 10506/100000 [3:13:32<14:31:48,  1.71it/s]
Train steps ... :  11%|█         | 10507/100000 [3:13:32<14:32:06,  1.71it/s]
Train steps ... :  11%|█         | 10508/100000 [3:13:33<14:31:54,  1.71it/s]
Train steps ... :  11%|█         | 10509/100000 [3:13:34<14:32:06,  1.71it/s]
Train steps ... :  11%|█         | 10510/100000 [3:13:34<14:32:37,  1.71it/s]
Train steps ... :  11%|█         | 10511/100000 [3:13:35<14:31:59,  1.71it/s]
Train steps ... :  11%|█         | 10512/100000 [3:13:35<14:31:09,  1.71it/s]
Train steps ... :  11%|█         | 10513/100000 [3:13:36<14:31:06,  1.71it/s]
Train steps ... :  11%|█         | 10514/100000 [3:13:36<14:30:46,  1.71it/s]
Train steps ... :  11%|█         | 10515/100000 [3:13:37<14:30:47,  1.71it/s]
Train steps ... :  11%|█         | 10516/100000 [3:13:38<14:31:46,  1.71it/s]
Train steps ... :  11%|█         | 10517/100000 [3:13:38<14:31:32,  1.71it/s]
Train steps ... :  11%|█         | 10518/100000 [3:13:39<14:31:57,  1.71it/s]
Train steps ... :  11%|█         | 10519/100000 [3:13:39<14:31:53,  1.71it/s]
Train steps ... :  11%|█         | 10520/100000 [3:13:40<14:31:52,  1.71it/s]
Train steps ... :  11%|█         | 10521/100000 [3:13:41<14:31:15,  1.71it/s]
Train steps ... :  11%|█         | 10522/100000 [3:13:41<14:31:50,  1.71it/s]
Train steps ... :  11%|█         | 10523/100000 [3:13:42<14:31:24,  1.71it/s]
Train steps ... :  11%|█         | 10524/100000 [3:13:42<14:31:22,  1.71it/s]
Train steps ... :  11%|█         | 10525/100000 [3:13:43<14:31:03,  1.71it/s]Step... (10525 / 100000 | Loss: 0.8819776773452759, Learning Rate: 8.992462311557788e-05)
+
                                                                             
Step... (10525 / 100000 | Loss: 1.3110902309417725, Learning Rate: 8.992462311557788e-05)
+
Train steps ... :  11%|█         | 10525/100000 [3:13:43<14:31:03,  1.71it/s]
Train steps ... :  11%|█         | 10526/100000 [3:13:43<14:31:20,  1.71it/s]
Train steps ... :  11%|█         | 10527/100000 [3:13:44<14:31:46,  1.71it/s]
Train steps ... :  11%|█         | 10528/100000 [3:13:45<14:31:29,  1.71it/s]
Train steps ... :  11%|█         | 10529/100000 [3:13:45<14:31:11,  1.71it/s]
Train steps ... :  11%|█         | 10530/100000 [3:13:46<14:31:27,  1.71it/s]
Train steps ... :  11%|█         | 10531/100000 [3:13:46<14:31:35,  1.71it/s]
Train steps ... :  11%|█         | 10532/100000 [3:13:47<14:32:27,  1.71it/s]
Train steps ... :  11%|█         | 10533/100000 [3:13:48<14:32:28,  1.71it/s]
Train steps ... :  11%|█         | 10534/100000 [3:13:48<14:32:05,  1.71it/s]
Train steps ... :  11%|█         | 10535/100000 [3:13:49<14:31:51,  1.71it/s]
Train steps ... :  11%|█         | 10536/100000 [3:13:49<14:32:02,  1.71it/s]
Train steps ... :  11%|█         | 10537/100000 [3:13:50<14:31:27,  1.71it/s]
Train steps ... :  11%|█         | 10538/100000 [3:13:50<14:30:39,  1.71it/s]
Train steps ... :  11%|█         | 10539/100000 [3:13:51<14:30:52,  1.71it/s]
Train steps ... :  11%|█         | 10540/100000 [3:13:52<14:31:17,  1.71it/s]
Train steps ... :  11%|█         | 10541/100000 [3:13:52<14:31:05,  1.71it/s]
Train steps ... :  11%|█         | 10542/100000 [3:13:53<14:31:55,  1.71it/s]
Train steps ... :  11%|█         | 10543/100000 [3:13:53<14:32:29,  1.71it/s]
Train steps ... :  11%|█         | 10544/100000 [3:13:54<14:31:26,  1.71it/s]
Train steps ... :  11%|█         | 10545/100000 [3:13:55<14:30:51,  1.71it/s]
Train steps ... :  11%|█         | 10546/100000 [3:13:55<14:30:47,  1.71it/s]
Train steps ... :  11%|█         | 10547/100000 [3:13:56<14:33:14,  1.71it/s]
Train steps ... :  11%|█         | 10548/100000 [3:13:56<14:32:00,  1.71it/s]
Train steps ... :  11%|█         | 10549/100000 [3:13:57<14:31:48,  1.71it/s]
Train steps ... :  11%|█         | 10550/100000 [3:13:57<14:31:18,  1.71it/s]Step... (10550 / 100000 | Loss: 1.6927626132965088, Learning Rate: 8.989949748743719e-05)
+
                                                                             
Step... (10550 / 100000 | Loss: 1.3304309844970703, Learning Rate: 8.989949748743719e-05)
+
Train steps ... :  11%|█         | 10550/100000 [3:13:58<14:31:18,  1.71it/s]
Train steps ... :  11%|█         | 10551/100000 [3:13:58<14:31:08,  1.71it/s]
Train steps ... :  11%|█         | 10552/100000 [3:13:59<14:30:31,  1.71it/s]
Train steps ... :  11%|█         | 10553/100000 [3:13:59<14:30:51,  1.71it/s]
Train steps ... :  11%|█         | 10554/100000 [3:14:00<14:29:59,  1.71it/s]
Train steps ... :  11%|█         | 10555/100000 [3:14:00<14:29:59,  1.71it/s]
Train steps ... :  11%|█         | 10556/100000 [3:14:01<14:30:20,  1.71it/s]
Train steps ... :  11%|█         | 10557/100000 [3:14:02<14:31:09,  1.71it/s]
Train steps ... :  11%|█         | 10558/100000 [3:14:02<14:30:52,  1.71it/s]
Train steps ... :  11%|█         | 10559/100000 [3:14:03<14:30:15,  1.71it/s]
Train steps ... :  11%|█         | 10560/100000 [3:14:03<14:30:29,  1.71it/s]
Train steps ... :  11%|█         | 10561/100000 [3:14:04<14:30:16,  1.71it/s]
Train steps ... :  11%|█         | 10562/100000 [3:14:04<14:30:29,  1.71it/s]
Train steps ... :  11%|█         | 10563/100000 [3:14:05<14:31:32,  1.71it/s]
Train steps ... :  11%|█         | 10564/100000 [3:14:06<14:31:22,  1.71it/s]
Train steps ... :  11%|█         | 10565/100000 [3:14:06<14:30:57,  1.71it/s]
Train steps ... :  11%|█         | 10566/100000 [3:14:07<14:31:48,  1.71it/s]
Train steps ... :  11%|█         | 10567/100000 [3:14:07<14:31:23,  1.71it/s]
Train steps ... :  11%|█         | 10568/100000 [3:14:08<14:31:00,  1.71it/s]
Train steps ... :  11%|█         | 10569/100000 [3:14:09<14:30:43,  1.71it/s]
Train steps ... :  11%|█         | 10570/100000 [3:14:09<14:30:40,  1.71it/s]
Train steps ... :  11%|█         | 10571/100000 [3:14:10<14:31:55,  1.71it/s]
Train steps ... :  11%|█         | 10572/100000 [3:14:10<14:31:34,  1.71it/s]
Train steps ... :  11%|█         | 10573/100000 [3:14:11<14:30:54,  1.71it/s]
Train steps ... :  11%|█         | 10574/100000 [3:14:11<14:30:28,  1.71it/s]
Train steps ... :  11%|█         | 10575/100000 [3:14:12<14:30:12,  1.71it/s]Step... (10575 / 100000 | Loss: 1.2397079467773438, Learning Rate: 8.987437185929649e-05)
+
                                                                             
Step... (10575 / 100000 | Loss: 0.9942618608474731, Learning Rate: 8.987437185929649e-05)
+
Train steps ... :  11%|█         | 10575/100000 [3:14:12<14:30:12,  1.71it/s]
Train steps ... :  11%|█         | 10576/100000 [3:14:13<14:30:37,  1.71it/s]
Train steps ... :  11%|█         | 10577/100000 [3:14:13<14:31:00,  1.71it/s]
Train steps ... :  11%|█         | 10578/100000 [3:14:14<14:31:36,  1.71it/s]
Train steps ... :  11%|█         | 10579/100000 [3:14:14<14:31:30,  1.71it/s]
Train steps ... :  11%|█         | 10580/100000 [3:14:15<14:30:46,  1.71it/s]
Train steps ... :  11%|█         | 10581/100000 [3:14:16<14:31:29,  1.71it/s]
Train steps ... :  11%|█         | 10582/100000 [3:14:16<14:30:46,  1.71it/s]
Train steps ... :  11%|█         | 10583/100000 [3:14:17<14:30:13,  1.71it/s]
Train steps ... :  11%|█         | 10584/100000 [3:14:17<14:30:57,  1.71it/s]
Train steps ... :  11%|█         | 10585/100000 [3:14:18<14:30:56,  1.71it/s]
Train steps ... :  11%|█         | 10586/100000 [3:14:19<14:30:25,  1.71it/s]
Train steps ... :  11%|█         | 10587/100000 [3:14:19<14:31:42,  1.71it/s]
Train steps ... :  11%|█         | 10588/100000 [3:14:20<14:31:37,  1.71it/s]
Train steps ... :  11%|█         | 10589/100000 [3:14:20<14:31:10,  1.71it/s]
Train steps ... :  11%|█         | 10590/100000 [3:14:21<14:30:22,  1.71it/s]
Train steps ... :  11%|█         | 10591/100000 [3:14:21<14:31:01,  1.71it/s]
Train steps ... :  11%|█         | 10592/100000 [3:14:22<14:32:54,  1.71it/s]
Train steps ... :  11%|█         | 10593/100000 [3:14:23<14:31:44,  1.71it/s]
Train steps ... :  11%|█         | 10594/100000 [3:14:23<14:31:03,  1.71it/s]
Train steps ... :  11%|█         | 10595/100000 [3:14:24<14:30:49,  1.71it/s]
Train steps ... :  11%|█         | 10596/100000 [3:14:24<14:31:36,  1.71it/s]
Train steps ... :  11%|█         | 10597/100000 [3:14:25<14:30:56,  1.71it/s]
Train steps ... :  11%|█         | 10598/100000 [3:14:26<14:31:23,  1.71it/s]
Train steps ... :  11%|█         | 10599/100000 [3:14:26<14:31:03,  1.71it/s]
Train steps ... :  11%|█         | 10600/100000 [3:14:27<14:30:59,  1.71it/s]Step... (10600 / 100000 | Loss: 1.565263032913208, Learning Rate: 8.984924623115579e-05)
+
                                                                             
Step... (10600 / 100000 | Loss: 1.3982948064804077, Learning Rate: 8.984924623115579e-05)
+
Train steps ... :  11%|█         | 10600/100000 [3:14:27<14:30:59,  1.71it/s]
Train steps ... :  11%|█         | 10601/100000 [3:14:27<14:31:20,  1.71it/s]
Train steps ... :  11%|█         | 10602/100000 [3:14:28<14:30:39,  1.71it/s]
Train steps ... :  11%|█         | 10603/100000 [3:14:28<14:30:42,  1.71it/s]
Train steps ... :  11%|█         | 10604/100000 [3:14:29<14:31:43,  1.71it/s]
Train steps ... :  11%|█         | 10605/100000 [3:14:30<14:31:29,  1.71it/s]
Train steps ... :  11%|█         | 10606/100000 [3:14:30<14:30:57,  1.71it/s]
Train steps ... :  11%|█         | 10607/100000 [3:14:31<14:31:52,  1.71it/s]
Train steps ... :  11%|█         | 10608/100000 [3:14:31<14:32:41,  1.71it/s]
Train steps ... :  11%|█         | 10609/100000 [3:14:32<14:31:09,  1.71it/s]
Train steps ... :  11%|█         | 10610/100000 [3:14:33<14:30:48,  1.71it/s]
Train steps ... :  11%|█         | 10611/100000 [3:14:33<14:29:58,  1.71it/s]
Train steps ... :  11%|█         | 10612/100000 [3:14:34<14:31:04,  1.71it/s]
Train steps ... :  11%|█         | 10613/100000 [3:14:34<14:31:05,  1.71it/s]
Train steps ... :  11%|█         | 10614/100000 [3:14:35<14:30:56,  1.71it/s]
Train steps ... :  11%|█         | 10615/100000 [3:14:35<14:30:29,  1.71it/s]
Train steps ... :  11%|█         | 10616/100000 [3:14:36<14:30:30,  1.71it/s]
Train steps ... :  11%|█         | 10617/100000 [3:14:37<14:30:05,  1.71it/s]
Train steps ... :  11%|█         | 10618/100000 [3:14:37<14:29:43,  1.71it/s]
Train steps ... :  11%|█         | 10619/100000 [3:14:38<14:30:49,  1.71it/s]
Train steps ... :  11%|█         | 10620/100000 [3:14:38<14:30:50,  1.71it/s]
Train steps ... :  11%|█         | 10621/100000 [3:14:39<14:32:55,  1.71it/s]
Train steps ... :  11%|█         | 10622/100000 [3:14:40<14:33:02,  1.71it/s]
Train steps ... :  11%|█         | 10623/100000 [3:14:40<14:30:46,  1.71it/s]
Train steps ... :  11%|█         | 10624/100000 [3:14:41<14:30:54,  1.71it/s]
Train steps ... :  11%|█         | 10625/100000 [3:14:41<14:30:11,  1.71it/s]Step... (10625 / 100000 | Loss: 0.9526949524879456, Learning Rate: 8.982412060301508e-05)
+
                                                                             
Step... (10625 / 100000 | Loss: 1.2240221500396729, Learning Rate: 8.982412060301508e-05)
+
Train steps ... :  11%|█         | 10625/100000 [3:14:42<14:30:11,  1.71it/s]
Train steps ... :  11%|█         | 10626/100000 [3:14:42<14:31:16,  1.71it/s]
Train steps ... :  11%|█         | 10627/100000 [3:14:42<14:30:39,  1.71it/s]
Train steps ... :  11%|█         | 10628/100000 [3:14:43<14:30:22,  1.71it/s]
Train steps ... :  11%|█         | 10629/100000 [3:14:44<14:30:52,  1.71it/s]
Train steps ... :  11%|█         | 10630/100000 [3:14:44<14:31:06,  1.71it/s]
Train steps ... :  11%|█         | 10631/100000 [3:14:45<14:30:16,  1.71it/s]
Train steps ... :  11%|█         | 10632/100000 [3:14:45<14:30:42,  1.71it/s]
Train steps ... :  11%|█         | 10633/100000 [3:14:46<14:31:37,  1.71it/s]
Train steps ... :  11%|█         | 10634/100000 [3:14:47<14:32:04,  1.71it/s]
Train steps ... :  11%|█         | 10635/100000 [3:14:47<14:32:28,  1.71it/s]
Train steps ... :  11%|█         | 10636/100000 [3:14:48<14:32:31,  1.71it/s]
Train steps ... :  11%|█         | 10637/100000 [3:14:48<14:31:43,  1.71it/s]
Train steps ... :  11%|█         | 10638/100000 [3:14:49<14:30:41,  1.71it/s]
Train steps ... :  11%|█         | 10639/100000 [3:14:50<14:30:51,  1.71it/s]
Train steps ... :  11%|█         | 10640/100000 [3:14:50<14:30:08,  1.71it/s]
Train steps ... :  11%|█         | 10641/100000 [3:14:51<14:30:53,  1.71it/s]
Train steps ... :  11%|█         | 10642/100000 [3:14:51<14:30:04,  1.71it/s]
Train steps ... :  11%|█         | 10643/100000 [3:14:52<14:32:06,  1.71it/s]
Train steps ... :  11%|█         | 10644/100000 [3:14:52<14:30:30,  1.71it/s]
Train steps ... :  11%|█         | 10645/100000 [3:14:53<14:31:11,  1.71it/s]
Train steps ... :  11%|█         | 10646/100000 [3:14:54<14:32:26,  1.71it/s]
Train steps ... :  11%|█         | 10647/100000 [3:14:54<14:33:12,  1.71it/s]
Train steps ... :  11%|█         | 10648/100000 [3:14:55<14:29:36,  1.71it/s]
Train steps ... :  11%|█         | 10649/100000 [3:14:55<14:29:53,  1.71it/s]
Train steps ... :  11%|█         | 10650/100000 [3:14:56<14:29:28,  1.71it/s]Step... (10650 / 100000 | Loss: 1.4758002758026123, Learning Rate: 8.979899497487438e-05)
+
                                                                             
Step... (10650 / 100000 | Loss: 1.2499860525131226, Learning Rate: 8.979899497487438e-05)
+
Train steps ... :  11%|█         | 10650/100000 [3:14:56<14:29:28,  1.71it/s]
Train steps ... :  11%|█         | 10651/100000 [3:14:57<14:31:12,  1.71it/s]
Train steps ... :  11%|█         | 10652/100000 [3:14:57<14:30:01,  1.71it/s]
Train steps ... :  11%|█         | 10653/100000 [3:14:58<14:30:20,  1.71it/s]
Train steps ... :  11%|█         | 10654/100000 [3:14:58<14:31:40,  1.71it/s]
Train steps ... :  11%|█         | 10655/100000 [3:14:59<14:31:12,  1.71it/s]
Train steps ... :  11%|█         | 10656/100000 [3:14:59<14:32:32,  1.71it/s]
Train steps ... :  11%|█         | 10657/100000 [3:15:00<14:31:25,  1.71it/s]
Train steps ... :  11%|█         | 10658/100000 [3:15:01<14:31:29,  1.71it/s]
Train steps ... :  11%|█         | 10659/100000 [3:15:01<14:31:37,  1.71it/s]
Train steps ... :  11%|█         | 10660/100000 [3:15:02<14:32:53,  1.71it/s]
Train steps ... :  11%|█         | 10661/100000 [3:15:02<14:31:15,  1.71it/s]
Train steps ... :  11%|█         | 10662/100000 [3:15:03<14:30:46,  1.71it/s]
Train steps ... :  11%|█         | 10663/100000 [3:15:04<14:31:03,  1.71it/s]
Train steps ... :  11%|█         | 10664/100000 [3:15:04<14:30:19,  1.71it/s]
Train steps ... :  11%|█         | 10665/100000 [3:15:05<14:31:12,  1.71it/s]
Train steps ... :  11%|█         | 10666/100000 [3:15:05<14:31:41,  1.71it/s]
Train steps ... :  11%|█         | 10667/100000 [3:15:06<14:31:22,  1.71it/s]
Train steps ... :  11%|█         | 10668/100000 [3:15:06<14:30:51,  1.71it/s]
Train steps ... :  11%|█         | 10669/100000 [3:15:07<14:30:40,  1.71it/s]
Train steps ... :  11%|█         | 10670/100000 [3:15:08<14:30:20,  1.71it/s]
Train steps ... :  11%|█         | 10671/100000 [3:15:08<14:30:10,  1.71it/s]
Train steps ... :  11%|█         | 10672/100000 [3:15:09<14:30:29,  1.71it/s]
Train steps ... :  11%|█         | 10673/100000 [3:15:09<14:29:32,  1.71it/s]
Train steps ... :  11%|█         | 10674/100000 [3:15:10<14:31:12,  1.71it/s]
Train steps ... :  11%|█         | 10675/100000 [3:15:11<14:32:06,  1.71it/s]Step... (10675 / 100000 | Loss: 0.9122167825698853, Learning Rate: 8.977386934673368e-05)
+
                                                                             
Step... (10675 / 100000 | Loss: 0.9689178466796875, Learning Rate: 8.977386934673368e-05)
+
Train steps ... :  11%|█         | 10675/100000 [3:15:11<14:32:06,  1.71it/s]
Train steps ... :  11%|█         | 10676/100000 [3:15:11<14:31:48,  1.71it/s]
Train steps ... :  11%|█         | 10677/100000 [3:15:12<14:30:44,  1.71it/s]
Train steps ... :  11%|█         | 10678/100000 [3:15:12<14:30:13,  1.71it/s]
Train steps ... :  11%|█         | 10679/100000 [3:15:13<14:29:47,  1.71it/s]
Train steps ... :  11%|█         | 10680/100000 [3:15:13<14:31:34,  1.71it/s]
Train steps ... :  11%|█         | 10681/100000 [3:15:14<14:31:04,  1.71it/s]
Train steps ... :  11%|█         | 10682/100000 [3:15:15<14:30:47,  1.71it/s]
Train steps ... :  11%|█         | 10683/100000 [3:15:15<14:30:36,  1.71it/s]
Train steps ... :  11%|█         | 10684/100000 [3:15:16<14:29:58,  1.71it/s]
Train steps ... :  11%|█         | 10685/100000 [3:15:16<14:30:55,  1.71it/s]
Train steps ... :  11%|█         | 10686/100000 [3:15:17<14:31:16,  1.71it/s]
Train steps ... :  11%|█         | 10687/100000 [3:15:18<14:30:05,  1.71it/s]
Train steps ... :  11%|█         | 10688/100000 [3:15:18<14:30:33,  1.71it/s]
Train steps ... :  11%|█         | 10689/100000 [3:15:19<14:29:51,  1.71it/s]
Train steps ... :  11%|█         | 10690/100000 [3:15:19<14:29:44,  1.71it/s]
Train steps ... :  11%|█         | 10691/100000 [3:15:20<14:29:18,  1.71it/s]
Train steps ... :  11%|█         | 10692/100000 [3:15:20<14:29:22,  1.71it/s]
Train steps ... :  11%|█         | 10693/100000 [3:15:21<14:29:43,  1.71it/s]
Train steps ... :  11%|█         | 10694/100000 [3:15:22<14:29:46,  1.71it/s]
Train steps ... :  11%|█         | 10695/100000 [3:15:22<14:30:02,  1.71it/s]
Train steps ... :  11%|█         | 10696/100000 [3:15:23<14:29:10,  1.71it/s]
Train steps ... :  11%|█         | 10697/100000 [3:15:23<14:29:53,  1.71it/s]
Train steps ... :  11%|█         | 10698/100000 [3:15:24<14:30:25,  1.71it/s]
Train steps ... :  11%|█         | 10699/100000 [3:15:25<14:31:27,  1.71it/s]
Train steps ... :  11%|█         | 10700/100000 [3:15:25<14:30:53,  1.71it/s]Step... (10700 / 100000 | Loss: 0.9678511619567871, Learning Rate: 8.974874371859296e-05)
+
                                                                             
Step... (10700 / 100000 | Loss: 1.021416425704956, Learning Rate: 8.974874371859296e-05)
+
Train steps ... :  11%|█         | 10700/100000 [3:15:26<14:30:53,  1.71it/s]
Train steps ... :  11%|█         | 10701/100000 [3:15:26<14:31:51,  1.71it/s]
Train steps ... :  11%|█         | 10702/100000 [3:15:26<14:32:21,  1.71it/s]
Train steps ... :  11%|█         | 10703/100000 [3:15:27<14:31:28,  1.71it/s]
Train steps ... :  11%|█         | 10704/100000 [3:15:28<14:30:52,  1.71it/s]
Train steps ... :  11%|█         | 10705/100000 [3:15:28<14:30:51,  1.71it/s]
Train steps ... :  11%|█         | 10706/100000 [3:15:29<14:30:31,  1.71it/s]
Train steps ... :  11%|█         | 10707/100000 [3:15:29<14:30:42,  1.71it/s]
Train steps ... :  11%|█         | 10708/100000 [3:15:30<14:30:30,  1.71it/s]
Train steps ... :  11%|█         | 10709/100000 [3:15:30<14:29:39,  1.71it/s]
Train steps ... :  11%|█         | 10710/100000 [3:15:31<14:29:28,  1.71it/s]
Train steps ... :  11%|█         | 10711/100000 [3:15:32<14:29:25,  1.71it/s]
Train steps ... :  11%|█         | 10712/100000 [3:15:32<14:31:21,  1.71it/s]
Train steps ... :  11%|█         | 10713/100000 [3:15:33<14:30:20,  1.71it/s]
Train steps ... :  11%|█         | 10714/100000 [3:15:33<14:30:26,  1.71it/s]
Train steps ... :  11%|█         | 10715/100000 [3:15:34<14:31:11,  1.71it/s]
Train steps ... :  11%|█         | 10716/100000 [3:15:35<14:31:53,  1.71it/s]
Train steps ... :  11%|█         | 10717/100000 [3:15:35<14:31:40,  1.71it/s]
Train steps ... :  11%|█         | 10718/100000 [3:15:36<14:30:23,  1.71it/s]
Train steps ... :  11%|█         | 10719/100000 [3:15:36<14:29:56,  1.71it/s]
Train steps ... :  11%|█         | 10720/100000 [3:15:37<14:30:05,  1.71it/s]
Train steps ... :  11%|█         | 10721/100000 [3:15:37<14:31:18,  1.71it/s]
Train steps ... :  11%|█         | 10722/100000 [3:15:38<14:29:39,  1.71it/s]
Train steps ... :  11%|█         | 10723/100000 [3:15:39<14:29:14,  1.71it/s]
Train steps ... :  11%|█         | 10724/100000 [3:15:39<14:31:26,  1.71it/s]
Train steps ... :  11%|█         | 10725/100000 [3:15:40<14:30:49,  1.71it/s]Step... (10725 / 100000 | Loss: 1.9477779865264893, Learning Rate: 8.972361809045227e-05)
+
                                                                             
Step... (10725 / 100000 | Loss: 0.882428765296936, Learning Rate: 8.972361809045227e-05)
+
Train steps ... :  11%|█         | 10725/100000 [3:15:40<14:30:49,  1.71it/s]
Train steps ... :  11%|█         | 10726/100000 [3:15:40<14:30:28,  1.71it/s]
Train steps ... :  11%|█         | 10727/100000 [3:15:41<14:31:38,  1.71it/s]
Train steps ... :  11%|█         | 10728/100000 [3:15:42<14:29:56,  1.71it/s]
Train steps ... :  11%|█         | 10729/100000 [3:15:42<14:30:29,  1.71it/s]
Train steps ... :  11%|█         | 10730/100000 [3:15:43<14:30:01,  1.71it/s]
Train steps ... :  11%|█         | 10731/100000 [3:15:43<14:29:47,  1.71it/s]
Train steps ... :  11%|█         | 10732/100000 [3:15:44<14:29:44,  1.71it/s]
Train steps ... :  11%|█         | 10733/100000 [3:15:44<14:32:31,  1.71it/s]
Train steps ... :  11%|█         | 10734/100000 [3:15:45<14:30:11,  1.71it/s]
Train steps ... :  11%|█         | 10735/100000 [3:15:46<14:30:48,  1.71it/s]
Train steps ... :  11%|█         | 10736/100000 [3:15:46<14:29:54,  1.71it/s]
Train steps ... :  11%|█         | 10737/100000 [3:15:47<14:29:26,  1.71it/s]
Train steps ... :  11%|█         | 10738/100000 [3:15:47<14:29:48,  1.71it/s]
Train steps ... :  11%|█         | 10739/100000 [3:15:48<14:29:17,  1.71it/s]
Train steps ... :  11%|█         | 10740/100000 [3:15:49<14:28:48,  1.71it/s]
Train steps ... :  11%|█         | 10741/100000 [3:15:49<14:28:56,  1.71it/s]
Train steps ... :  11%|█         | 10742/100000 [3:15:50<14:29:41,  1.71it/s]
Train steps ... :  11%|█         | 10743/100000 [3:15:50<14:30:00,  1.71it/s]
Train steps ... :  11%|█         | 10744/100000 [3:15:51<14:29:51,  1.71it/s]
Train steps ... :  11%|█         | 10745/100000 [3:15:52<14:29:40,  1.71it/s]
Train steps ... :  11%|█         | 10746/100000 [3:15:52<14:29:34,  1.71it/s]
Train steps ... :  11%|█         | 10747/100000 [3:15:53<14:29:07,  1.71it/s]
Train steps ... :  11%|█         | 10748/100000 [3:15:53<14:29:03,  1.71it/s]
Train steps ... :  11%|█         | 10749/100000 [3:15:54<14:28:58,  1.71it/s]
Train steps ... :  11%|█         | 10750/100000 [3:15:54<14:28:32,  1.71it/s]Step... (10750 / 100000 | Loss: 1.7355679273605347, Learning Rate: 8.969849246231157e-05)
+
                                                                             
Step... (10750 / 100000 | Loss: 1.1992912292480469, Learning Rate: 8.969849246231157e-05)
+
Train steps ... :  11%|█         | 10750/100000 [3:15:55<14:28:32,  1.71it/s]
Train steps ... :  11%|█         | 10751/100000 [3:15:55<14:28:48,  1.71it/s]
Train steps ... :  11%|█         | 10752/100000 [3:15:56<14:29:07,  1.71it/s]
Train steps ... :  11%|█         | 10753/100000 [3:15:56<14:29:38,  1.71it/s]
Train steps ... :  11%|█         | 10754/100000 [3:15:57<14:28:57,  1.71it/s]
Train steps ... :  11%|█         | 10755/100000 [3:15:57<14:28:41,  1.71it/s]
Train steps ... :  11%|█         | 10756/100000 [3:15:58<14:30:08,  1.71it/s]
Train steps ... :  11%|█         | 10757/100000 [3:15:59<14:30:01,  1.71it/s]
Train steps ... :  11%|█         | 10758/100000 [3:15:59<14:32:06,  1.71it/s]
Train steps ... :  11%|█         | 10759/100000 [3:16:00<14:30:42,  1.71it/s]
Train steps ... :  11%|█         | 10760/100000 [3:16:00<14:31:01,  1.71it/s]
Train steps ... :  11%|█         | 10761/100000 [3:16:01<14:30:19,  1.71it/s]
Train steps ... :  11%|█         | 10762/100000 [3:16:01<14:34:53,  1.70it/s]
Train steps ... :  11%|█         | 10763/100000 [3:16:02<14:34:20,  1.70it/s]
Train steps ... :  11%|█         | 10764/100000 [3:16:03<14:33:06,  1.70it/s]
Train steps ... :  11%|█         | 10765/100000 [3:16:03<14:31:28,  1.71it/s]
Train steps ... :  11%|█         | 10766/100000 [3:16:04<14:31:30,  1.71it/s]
Train steps ... :  11%|█         | 10767/100000 [3:16:04<14:31:21,  1.71it/s]
Train steps ... :  11%|█         | 10768/100000 [3:16:05<14:30:37,  1.71it/s]
Train steps ... :  11%|█         | 10769/100000 [3:16:06<14:30:25,  1.71it/s]
Train steps ... :  11%|█         | 10770/100000 [3:16:06<14:29:53,  1.71it/s]
Train steps ... :  11%|█         | 10771/100000 [3:16:07<14:30:06,  1.71it/s]
Train steps ... :  11%|█         | 10772/100000 [3:16:07<14:29:29,  1.71it/s]
Train steps ... :  11%|█         | 10773/100000 [3:16:08<14:29:56,  1.71it/s]
Train steps ... :  11%|█         | 10774/100000 [3:16:08<14:30:49,  1.71it/s]
Train steps ... :  11%|█         | 10775/100000 [3:16:09<14:29:26,  1.71it/s]Step... (10775 / 100000 | Loss: 1.3096238374710083, Learning Rate: 8.967336683417086e-05)
+
                                                                             
Step... (10775 / 100000 | Loss: 1.0108648538589478, Learning Rate: 8.967336683417086e-05)
+
Train steps ... :  11%|█         | 10775/100000 [3:16:09<14:29:26,  1.71it/s]
Train steps ... :  11%|█         | 10776/100000 [3:16:10<14:30:35,  1.71it/s]
Train steps ... :  11%|█         | 10777/100000 [3:16:10<14:31:22,  1.71it/s]
Train steps ... :  11%|█         | 10778/100000 [3:16:11<14:30:40,  1.71it/s]
Train steps ... :  11%|█         | 10779/100000 [3:16:11<14:29:39,  1.71it/s]
Train steps ... :  11%|█         | 10780/100000 [3:16:12<14:29:36,  1.71it/s]
Train steps ... :  11%|█         | 10781/100000 [3:16:13<14:30:05,  1.71it/s]
Train steps ... :  11%|█         | 10782/100000 [3:16:13<14:28:49,  1.71it/s]
Train steps ... :  11%|█         | 10783/100000 [3:16:14<14:29:50,  1.71it/s]
Train steps ... :  11%|█         | 10784/100000 [3:16:14<14:30:06,  1.71it/s]
Train steps ... :  11%|█         | 10785/100000 [3:16:15<14:29:48,  1.71it/s]
Train steps ... :  11%|█         | 10786/100000 [3:16:15<14:30:39,  1.71it/s]
Train steps ... :  11%|█         | 10787/100000 [3:16:16<14:30:04,  1.71it/s]
Train steps ... :  11%|█         | 10788/100000 [3:16:17<14:33:07,  1.70it/s]
Train steps ... :  11%|█         | 10789/100000 [3:16:17<14:29:47,  1.71it/s]
Train steps ... :  11%|█         | 10790/100000 [3:16:18<14:31:16,  1.71it/s]
Train steps ... :  11%|█         | 10791/100000 [3:16:18<14:29:43,  1.71it/s]
Train steps ... :  11%|█         | 10792/100000 [3:16:19<14:29:16,  1.71it/s]
Train steps ... :  11%|█         | 10793/100000 [3:16:20<14:29:35,  1.71it/s]
Train steps ... :  11%|█         | 10794/100000 [3:16:20<14:28:49,  1.71it/s]
Train steps ... :  11%|█         | 10795/100000 [3:16:21<14:28:37,  1.71it/s]
Train steps ... :  11%|█         | 10796/100000 [3:16:21<14:28:46,  1.71it/s]
Train steps ... :  11%|█         | 10797/100000 [3:16:22<14:31:11,  1.71it/s]
Train steps ... :  11%|█         | 10798/100000 [3:16:23<14:29:38,  1.71it/s]
Train steps ... :  11%|█         | 10799/100000 [3:16:23<14:29:39,  1.71it/s]
Train steps ... :  11%|█         | 10800/100000 [3:16:24<14:29:48,  1.71it/s]Step... (10800 / 100000 | Loss: 0.7305522561073303, Learning Rate: 8.964824120603016e-05)
+
                                                                             
Step... (10800 / 100000 | Loss: 1.1701890230178833, Learning Rate: 8.964824120603016e-05)
+
Train steps ... :  11%|█         | 10800/100000 [3:16:24<14:29:48,  1.71it/s]
Train steps ... :  11%|█         | 10801/100000 [3:16:24<14:30:38,  1.71it/s]
Train steps ... :  11%|█         | 10802/100000 [3:16:25<14:30:24,  1.71it/s]
Train steps ... :  11%|█         | 10803/100000 [3:16:25<14:30:06,  1.71it/s]
Train steps ... :  11%|█         | 10804/100000 [3:16:26<14:30:44,  1.71it/s]
Train steps ... :  11%|█         | 10805/100000 [3:16:27<14:30:57,  1.71it/s]
Train steps ... :  11%|█         | 10806/100000 [3:16:27<14:32:26,  1.70it/s]
Train steps ... :  11%|█         | 10807/100000 [3:16:28<14:30:15,  1.71it/s]
Train steps ... :  11%|█         | 10808/100000 [3:16:28<14:28:44,  1.71it/s]
Train steps ... :  11%|█         | 10809/100000 [3:16:29<14:28:20,  1.71it/s]
Train steps ... :  11%|█         | 10810/100000 [3:16:30<14:28:55,  1.71it/s]
Train steps ... :  11%|█         | 10811/100000 [3:16:30<14:28:52,  1.71it/s]
Train steps ... :  11%|█         | 10812/100000 [3:16:31<14:28:08,  1.71it/s]
Train steps ... :  11%|█         | 10813/100000 [3:16:31<14:29:49,  1.71it/s]
Train steps ... :  11%|█         | 10814/100000 [3:16:32<14:30:18,  1.71it/s]
Train steps ... :  11%|█         | 10815/100000 [3:16:32<14:29:47,  1.71it/s]
Train steps ... :  11%|█         | 10816/100000 [3:16:33<14:29:21,  1.71it/s]
Train steps ... :  11%|█         | 10817/100000 [3:16:34<14:30:52,  1.71it/s]
Train steps ... :  11%|█         | 10818/100000 [3:16:34<14:30:14,  1.71it/s]
Train steps ... :  11%|█         | 10819/100000 [3:16:35<14:31:14,  1.71it/s]
Train steps ... :  11%|█         | 10820/100000 [3:16:35<14:30:28,  1.71it/s]
Train steps ... :  11%|█         | 10821/100000 [3:16:36<14:30:07,  1.71it/s]
Train steps ... :  11%|█         | 10822/100000 [3:16:37<14:30:49,  1.71it/s]
Train steps ... :  11%|█         | 10823/100000 [3:16:37<14:30:48,  1.71it/s]
Train steps ... :  11%|█         | 10824/100000 [3:16:38<14:31:24,  1.71it/s]
Train steps ... :  11%|█         | 10825/100000 [3:16:38<14:31:21,  1.71it/s]Step... (10825 / 100000 | Loss: 1.388143539428711, Learning Rate: 8.962311557788945e-05)
+
                                                                             
Step... (10825 / 100000 | Loss: 1.7155908346176147, Learning Rate: 8.962311557788945e-05)
+
Train steps ... :  11%|█         | 10825/100000 [3:16:39<14:31:21,  1.71it/s]
Train steps ... :  11%|█         | 10826/100000 [3:16:39<14:31:14,  1.71it/s]
Train steps ... :  11%|█         | 10827/100000 [3:16:39<14:29:54,  1.71it/s]
Train steps ... :  11%|█         | 10828/100000 [3:16:40<14:30:49,  1.71it/s]
Train steps ... :  11%|█         | 10829/100000 [3:16:41<14:30:19,  1.71it/s]
Train steps ... :  11%|█         | 10830/100000 [3:16:41<14:30:01,  1.71it/s]
Train steps ... :  11%|█         | 10831/100000 [3:16:42<14:29:18,  1.71it/s]
Train steps ... :  11%|█         | 10832/100000 [3:16:42<14:29:09,  1.71it/s]
Train steps ... :  11%|█         | 10833/100000 [3:16:43<14:30:24,  1.71it/s]
Train steps ... :  11%|█         | 10834/100000 [3:16:44<14:30:02,  1.71it/s]
Train steps ... :  11%|█         | 10835/100000 [3:16:44<14:28:39,  1.71it/s]
Train steps ... :  11%|█         | 10836/100000 [3:16:45<14:30:15,  1.71it/s]
Train steps ... :  11%|█         | 10837/100000 [3:16:45<14:30:13,  1.71it/s]
Train steps ... :  11%|█         | 10838/100000 [3:16:46<14:34:44,  1.70it/s]
Train steps ... :  11%|█         | 10839/100000 [3:16:47<14:30:05,  1.71it/s]
Train steps ... :  11%|█         | 10840/100000 [3:16:47<14:30:45,  1.71it/s]
Train steps ... :  11%|█         | 10841/100000 [3:16:48<14:29:50,  1.71it/s]
Train steps ... :  11%|█         | 10842/100000 [3:16:48<14:29:59,  1.71it/s]
Train steps ... :  11%|█         | 10843/100000 [3:16:49<14:29:40,  1.71it/s]
Train steps ... :  11%|█         | 10844/100000 [3:16:49<14:29:48,  1.71it/s]
Train steps ... :  11%|█         | 10845/100000 [3:16:50<14:31:52,  1.70it/s]
Train steps ... :  11%|█         | 10846/100000 [3:16:51<14:32:33,  1.70it/s]
Train steps ... :  11%|█         | 10847/100000 [3:16:51<14:29:53,  1.71it/s]
Train steps ... :  11%|█         | 10848/100000 [3:16:52<14:29:27,  1.71it/s]
Train steps ... :  11%|█         | 10849/100000 [3:16:52<14:29:44,  1.71it/s]
Train steps ... :  11%|█         | 10850/100000 [3:16:53<14:29:44,  1.71it/s]Step... (10850 / 100000 | Loss: 1.8434278964996338, Learning Rate: 8.959798994974875e-05)
+
                                                                             
Step... (10850 / 100000 | Loss: 1.097142219543457, Learning Rate: 8.959798994974875e-05)
+
Train steps ... :  11%|█         | 10850/100000 [3:16:53<14:29:44,  1.71it/s]
Train steps ... :  11%|█         | 10851/100000 [3:16:54<14:30:07,  1.71it/s]
Train steps ... :  11%|█         | 10852/100000 [3:16:54<14:30:15,  1.71it/s]
Train steps ... :  11%|█         | 10853/100000 [3:16:55<14:30:16,  1.71it/s]
Train steps ... :  11%|█         | 10854/100000 [3:16:55<14:30:39,  1.71it/s]
Train steps ... :  11%|█         | 10855/100000 [3:16:56<14:29:48,  1.71it/s]
Train steps ... :  11%|█         | 10856/100000 [3:16:56<14:29:14,  1.71it/s]
Train steps ... :  11%|█         | 10857/100000 [3:16:57<14:28:49,  1.71it/s]
Train steps ... :  11%|█         | 10858/100000 [3:16:58<14:30:23,  1.71it/s]
Train steps ... :  11%|█         | 10859/100000 [3:16:58<14:33:51,  1.70it/s]
Train steps ... :  11%|█         | 10860/100000 [3:16:59<14:33:02,  1.70it/s]
Train steps ... :  11%|█         | 10861/100000 [3:16:59<14:31:23,  1.70it/s]
Train steps ... :  11%|█         | 10862/100000 [3:17:00<14:31:17,  1.71it/s]
Train steps ... :  11%|█         | 10863/100000 [3:17:01<14:30:19,  1.71it/s]
Train steps ... :  11%|█         | 10864/100000 [3:17:01<14:30:02,  1.71it/s]
Train steps ... :  11%|█         | 10865/100000 [3:17:02<14:28:47,  1.71it/s]
Train steps ... :  11%|█         | 10866/100000 [3:17:02<14:28:18,  1.71it/s]
Train steps ... :  11%|█         | 10867/100000 [3:17:03<14:30:49,  1.71it/s]
Train steps ... :  11%|█         | 10868/100000 [3:17:04<14:30:25,  1.71it/s]
Train steps ... :  11%|█         | 10869/100000 [3:17:04<14:28:25,  1.71it/s]
Train steps ... :  11%|█         | 10870/100000 [3:17:05<14:28:39,  1.71it/s]
Train steps ... :  11%|█         | 10871/100000 [3:17:05<14:28:43,  1.71it/s]
Train steps ... :  11%|█         | 10872/100000 [3:17:06<14:28:59,  1.71it/s]
Train steps ... :  11%|█         | 10873/100000 [3:17:06<14:28:17,  1.71it/s]
Train steps ... :  11%|█         | 10874/100000 [3:17:07<14:29:35,  1.71it/s]
Train steps ... :  11%|█         | 10875/100000 [3:17:08<14:29:43,  1.71it/s]Step... (10875 / 100000 | Loss: 1.1726012229919434, Learning Rate: 8.957286432160803e-05)
+
                                                                             
Step... (10875 / 100000 | Loss: 1.42820405960083, Learning Rate: 8.957286432160803e-05)
+
Train steps ... :  11%|█         | 10875/100000 [3:17:08<14:29:43,  1.71it/s]
Train steps ... :  11%|█         | 10876/100000 [3:17:08<14:30:10,  1.71it/s]
Train steps ... :  11%|█         | 10877/100000 [3:17:09<14:28:38,  1.71it/s]
Train steps ... :  11%|█         | 10878/100000 [3:17:09<14:28:25,  1.71it/s]
Train steps ... :  11%|█         | 10879/100000 [3:17:10<14:29:02,  1.71it/s]
Train steps ... :  11%|█         | 10880/100000 [3:17:11<14:28:50,  1.71it/s]
Train steps ... :  11%|█         | 10881/100000 [3:17:11<14:29:17,  1.71it/s]
Train steps ... :  11%|█         | 10882/100000 [3:17:12<14:28:23,  1.71it/s]
Train steps ... :  11%|█         | 10883/100000 [3:17:12<14:28:56,  1.71it/s]
Train steps ... :  11%|█         | 10884/100000 [3:17:13<14:28:20,  1.71it/s]
Train steps ... :  11%|█         | 10885/100000 [3:17:13<14:28:41,  1.71it/s]
Train steps ... :  11%|█         | 10886/100000 [3:17:14<14:29:10,  1.71it/s]
Train steps ... :  11%|█         | 10887/100000 [3:17:15<14:28:05,  1.71it/s]
Train steps ... :  11%|█         | 10888/100000 [3:17:15<14:28:42,  1.71it/s]
Train steps ... :  11%|█         | 10889/100000 [3:17:16<14:28:25,  1.71it/s]
Train steps ... :  11%|█         | 10890/100000 [3:17:16<14:30:22,  1.71it/s]
Train steps ... :  11%|█         | 10891/100000 [3:17:17<14:29:24,  1.71it/s]
Train steps ... :  11%|█         | 10892/100000 [3:17:18<14:28:41,  1.71it/s]
Train steps ... :  11%|█         | 10893/100000 [3:17:18<14:29:33,  1.71it/s]
Train steps ... :  11%|█         | 10894/100000 [3:17:19<14:30:26,  1.71it/s]
Train steps ... :  11%|█         | 10895/100000 [3:17:19<14:29:50,  1.71it/s]
Train steps ... :  11%|█         | 10896/100000 [3:17:20<14:30:47,  1.71it/s]
Train steps ... :  11%|█         | 10897/100000 [3:17:20<14:31:28,  1.70it/s]
Train steps ... :  11%|█         | 10898/100000 [3:17:21<14:28:24,  1.71it/s]
Train steps ... :  11%|█         | 10899/100000 [3:17:22<14:31:10,  1.70it/s]
Train steps ... :  11%|█         | 10900/100000 [3:17:22<14:29:58,  1.71it/s]Step... (10900 / 100000 | Loss: 1.0471278429031372, Learning Rate: 8.954773869346734e-05)
+
                                                                             
Step... (10900 / 100000 | Loss: 1.148500919342041, Learning Rate: 8.954773869346734e-05)
+
Train steps ... :  11%|█         | 10900/100000 [3:17:23<14:29:58,  1.71it/s]
Train steps ... :  11%|█         | 10901/100000 [3:17:23<14:31:10,  1.70it/s]
Train steps ... :  11%|█         | 10902/100000 [3:17:23<14:30:04,  1.71it/s]
Train steps ... :  11%|█         | 10903/100000 [3:17:24<14:29:42,  1.71it/s]
Train steps ... :  11%|█         | 10904/100000 [3:17:25<14:28:36,  1.71it/s]
Train steps ... :  11%|█         | 10905/100000 [3:17:25<14:29:46,  1.71it/s]
Train steps ... :  11%|█         | 10906/100000 [3:17:26<14:30:05,  1.71it/s]
Train steps ... :  11%|█         | 10907/100000 [3:17:26<14:30:42,  1.71it/s]
Train steps ... :  11%|█         | 10908/100000 [3:17:27<14:29:02,  1.71it/s]
Train steps ... :  11%|█         | 10909/100000 [3:17:28<14:29:15,  1.71it/s]
Train steps ... :  11%|█         | 10910/100000 [3:17:28<14:28:51,  1.71it/s]
Train steps ... :  11%|█         | 10911/100000 [3:17:29<14:29:03,  1.71it/s]
Train steps ... :  11%|█         | 10912/100000 [3:17:29<14:29:16,  1.71it/s]
Train steps ... :  11%|█         | 10913/100000 [3:17:30<14:28:42,  1.71it/s]
Train steps ... :  11%|█         | 10914/100000 [3:17:30<14:28:43,  1.71it/s]
Train steps ... :  11%|█         | 10915/100000 [3:17:31<14:28:20,  1.71it/s]
Train steps ... :  11%|█         | 10916/100000 [3:17:32<14:28:22,  1.71it/s]
Train steps ... :  11%|█         | 10917/100000 [3:17:32<14:28:13,  1.71it/s]
Train steps ... :  11%|█         | 10918/100000 [3:17:33<14:33:10,  1.70it/s]
Train steps ... :  11%|█         | 10919/100000 [3:17:33<14:33:48,  1.70it/s]
Train steps ... :  11%|█         | 10920/100000 [3:17:34<14:31:16,  1.70it/s]
Train steps ... :  11%|█         | 10921/100000 [3:17:35<14:29:24,  1.71it/s]
Train steps ... :  11%|█         | 10922/100000 [3:17:35<14:33:53,  1.70it/s]
Train steps ... :  11%|█         | 10923/100000 [3:17:36<14:29:49,  1.71it/s]
Train steps ... :  11%|█         | 10924/100000 [3:17:36<14:29:26,  1.71it/s]
Train steps ... :  11%|█         | 10925/100000 [3:17:37<14:28:25,  1.71it/s]Step... (10925 / 100000 | Loss: 1.1727542877197266, Learning Rate: 8.952261306532663e-05)
+
                                                                             
Step... (10925 / 100000 | Loss: 1.6228926181793213, Learning Rate: 8.952261306532663e-05)
+
Train steps ... :  11%|█         | 10925/100000 [3:17:37<14:28:25,  1.71it/s]
Train steps ... :  11%|█         | 10926/100000 [3:17:37<14:29:00,  1.71it/s]
Train steps ... :  11%|█         | 10927/100000 [3:17:38<14:28:14,  1.71it/s]
Train steps ... :  11%|█         | 10928/100000 [3:17:39<14:27:35,  1.71it/s]
Train steps ... :  11%|█         | 10929/100000 [3:17:39<14:27:50,  1.71it/s]
Train steps ... :  11%|█         | 10930/100000 [3:17:40<14:29:18,  1.71it/s]
Train steps ... :  11%|█         | 10931/100000 [3:17:40<14:31:01,  1.70it/s]
Train steps ... :  11%|█         | 10932/100000 [3:17:41<14:28:59,  1.71it/s]
Train steps ... :  11%|█         | 10933/100000 [3:17:42<14:30:16,  1.71it/s]
Train steps ... :  11%|█         | 10934/100000 [3:17:42<14:31:00,  1.70it/s]
Train steps ... :  11%|█         | 10935/100000 [3:17:43<14:29:18,  1.71it/s]
Train steps ... :  11%|█         | 10936/100000 [3:17:43<14:28:52,  1.71it/s]
Train steps ... :  11%|█         | 10937/100000 [3:17:44<14:30:18,  1.71it/s]
Train steps ... :  11%|█         | 10938/100000 [3:17:44<14:28:36,  1.71it/s]
Train steps ... :  11%|█         | 10939/100000 [3:17:45<14:27:39,  1.71it/s]
Train steps ... :  11%|█         | 10940/100000 [3:17:46<14:27:38,  1.71it/s]
Train steps ... :  11%|█         | 10941/100000 [3:17:46<14:27:05,  1.71it/s]
Train steps ... :  11%|█         | 10942/100000 [3:17:47<14:28:36,  1.71it/s]
Train steps ... :  11%|█         | 10943/100000 [3:17:47<14:28:42,  1.71it/s]
Train steps ... :  11%|█         | 10944/100000 [3:17:48<14:31:16,  1.70it/s]
Train steps ... :  11%|█         | 10945/100000 [3:17:49<14:29:24,  1.71it/s]
Train steps ... :  11%|█         | 10946/100000 [3:17:49<14:29:36,  1.71it/s]
Train steps ... :  11%|█         | 10947/100000 [3:17:50<14:31:24,  1.70it/s]
Train steps ... :  11%|█         | 10948/100000 [3:17:50<14:29:40,  1.71it/s]
Train steps ... :  11%|█         | 10949/100000 [3:17:51<14:27:50,  1.71it/s]
Train steps ... :  11%|█         | 10950/100000 [3:17:52<14:27:30,  1.71it/s]Step... (10950 / 100000 | Loss: 0.9399399757385254, Learning Rate: 8.949748743718594e-05)
+
                                                                             
Step... (10950 / 100000 | Loss: 1.2435369491577148, Learning Rate: 8.949748743718594e-05)
+
Train steps ... :  11%|█         | 10950/100000 [3:17:52<14:27:30,  1.71it/s]
Train steps ... :  11%|█         | 10951/100000 [3:17:52<14:30:17,  1.71it/s]
Train steps ... :  11%|█         | 10952/100000 [3:17:53<14:28:49,  1.71it/s]
Train steps ... :  11%|█         | 10953/100000 [3:17:53<14:28:18,  1.71it/s]
Train steps ... :  11%|█         | 10954/100000 [3:17:54<14:30:05,  1.71it/s]
Train steps ... :  11%|█         | 10955/100000 [3:17:54<14:28:36,  1.71it/s]
Train steps ... :  11%|█         | 10956/100000 [3:17:55<14:28:13,  1.71it/s]
Train steps ... :  11%|█         | 10957/100000 [3:17:56<14:28:46,  1.71it/s]
Train steps ... :  11%|█         | 10958/100000 [3:17:56<14:29:02,  1.71it/s]
Train steps ... :  11%|█         | 10959/100000 [3:17:57<14:28:45,  1.71it/s]
Train steps ... :  11%|█         | 10960/100000 [3:17:57<14:34:47,  1.70it/s]
Train steps ... :  11%|█         | 10961/100000 [3:17:58<14:30:53,  1.70it/s]
Train steps ... :  11%|█         | 10962/100000 [3:17:59<14:30:29,  1.70it/s]
Train steps ... :  11%|█         | 10963/100000 [3:17:59<14:29:57,  1.71it/s]
Train steps ... :  11%|█         | 10964/100000 [3:18:00<14:29:34,  1.71it/s]
Train steps ... :  11%|█         | 10965/100000 [3:18:00<14:28:50,  1.71it/s]
Train steps ... :  11%|█         | 10966/100000 [3:18:01<14:28:05,  1.71it/s]
Train steps ... :  11%|█         | 10967/100000 [3:18:01<14:27:20,  1.71it/s]
Train steps ... :  11%|█         | 10968/100000 [3:18:02<14:27:33,  1.71it/s]
Train steps ... :  11%|█         | 10969/100000 [3:18:03<14:27:08,  1.71it/s]
Train steps ... :  11%|█         | 10970/100000 [3:18:03<14:28:41,  1.71it/s]
Train steps ... :  11%|█         | 10971/100000 [3:18:04<14:27:24,  1.71it/s]
Train steps ... :  11%|█         | 10972/100000 [3:18:04<14:29:39,  1.71it/s]
Train steps ... :  11%|█         | 10973/100000 [3:18:05<14:31:18,  1.70it/s]
Train steps ... :  11%|█         | 10974/100000 [3:18:06<14:31:08,  1.70it/s]
Train steps ... :  11%|█         | 10975/100000 [3:18:06<14:29:10,  1.71it/s]Step... (10975 / 100000 | Loss: 1.1837830543518066, Learning Rate: 8.947236180904523e-05)
+
                                                                             
Step... (10975 / 100000 | Loss: 1.2734298706054688, Learning Rate: 8.947236180904523e-05)
+
Train steps ... :  11%|█         | 10975/100000 [3:18:07<14:29:10,  1.71it/s]
Train steps ... :  11%|█         | 10976/100000 [3:18:07<14:28:53,  1.71it/s]
Train steps ... :  11%|█         | 10977/100000 [3:18:07<14:32:41,  1.70it/s]
Train steps ... :  11%|█         | 10978/100000 [3:18:08<14:30:29,  1.70it/s]
Train steps ... :  11%|█         | 10979/100000 [3:18:09<14:30:36,  1.70it/s]
Train steps ... :  11%|█         | 10980/100000 [3:18:09<14:29:41,  1.71it/s]
Train steps ... :  11%|█         | 10981/100000 [3:18:10<14:28:11,  1.71it/s]
Train steps ... :  11%|█         | 10982/100000 [3:18:10<14:27:24,  1.71it/s]
Train steps ... :  11%|█         | 10983/100000 [3:18:11<14:27:47,  1.71it/s]
Train steps ... :  11%|█         | 10984/100000 [3:18:11<14:27:39,  1.71it/s]
Train steps ... :  11%|█         | 10985/100000 [3:18:12<14:29:34,  1.71it/s]
Train steps ... :  11%|█         | 10986/100000 [3:18:13<14:28:03,  1.71it/s]
Train steps ... :  11%|█         | 10987/100000 [3:18:13<14:28:02,  1.71it/s]
Train steps ... :  11%|█         | 10988/100000 [3:18:14<14:27:27,  1.71it/s]
Train steps ... :  11%|█         | 10989/100000 [3:18:14<14:27:07,  1.71it/s]
Train steps ... :  11%|█         | 10990/100000 [3:18:15<14:28:51,  1.71it/s]
Train steps ... :  11%|█         | 10991/100000 [3:18:16<14:28:01,  1.71it/s]
Train steps ... :  11%|█         | 10992/100000 [3:18:16<14:30:38,  1.70it/s]
Train steps ... :  11%|█         | 10993/100000 [3:18:17<14:28:13,  1.71it/s]
Train steps ... :  11%|█         | 10994/100000 [3:18:17<14:28:33,  1.71it/s]
Train steps ... :  11%|█         | 10995/100000 [3:18:18<14:27:42,  1.71it/s]
Train steps ... :  11%|█         | 10996/100000 [3:18:18<14:29:26,  1.71it/s]
Train steps ... :  11%|█         | 10997/100000 [3:18:19<14:28:29,  1.71it/s]
Train steps ... :  11%|█         | 10998/100000 [3:18:20<14:28:10,  1.71it/s]
Train steps ... :  11%|█         | 10999/100000 [3:18:20<14:27:23,  1.71it/s]
Train steps ... :  11%|█         | 11000/100000 [3:18:21<14:29:54,  1.71it/s]Step... (11000 / 100000 | Loss: 1.1818771362304688, Learning Rate: 8.944723618090453e-05)
+
                                                                             
Step... (11000 / 100000 | Loss: 1.8003695011138916, Learning Rate: 8.944723618090453e-05)
+
Train steps ... :  11%|█         | 11000/100000 [3:18:21<14:29:54,  1.71it/s]
Train steps ... :  11%|█         | 11001/100000 [3:18:21<14:28:51,  1.71it/s]
Train steps ... :  11%|█         | 11002/100000 [3:18:22<14:31:15,  1.70it/s]
Train steps ... :  11%|█         | 11003/100000 [3:18:23<14:28:38,  1.71it/s]
Train steps ... :  11%|█         | 11004/100000 [3:18:23<14:30:00,  1.70it/s]
Train steps ... :  11%|█         | 11005/100000 [3:18:24<14:27:16,  1.71it/s]
Train steps ... :  11%|█         | 11006/100000 [3:18:24<14:30:09,  1.70it/s]
Train steps ... :  11%|█         | 11007/100000 [3:18:25<14:26:39,  1.71it/s]
Train steps ... :  11%|█         | 11008/100000 [3:18:25<14:29:06,  1.71it/s]
Train steps ... :  11%|█         | 11009/100000 [3:18:26<14:29:06,  1.71it/s]
Train steps ... :  11%|█         | 11010/100000 [3:18:27<14:28:34,  1.71it/s]
Train steps ... :  11%|█         | 11011/100000 [3:18:27<14:28:50,  1.71it/s]
Train steps ... :  11%|█         | 11012/100000 [3:18:28<14:30:10,  1.70it/s]
Train steps ... :  11%|█         | 11013/100000 [3:18:28<14:30:51,  1.70it/s]
Train steps ... :  11%|█         | 11014/100000 [3:18:29<14:30:36,  1.70it/s]
Train steps ... :  11%|█         | 11015/100000 [3:18:30<14:30:45,  1.70it/s]
Train steps ... :  11%|█         | 11016/100000 [3:18:30<14:31:24,  1.70it/s]
Train steps ... :  11%|█         | 11017/100000 [3:18:31<14:29:55,  1.70it/s]
Train steps ... :  11%|█         | 11018/100000 [3:18:31<14:28:55,  1.71it/s]
Train steps ... :  11%|█         | 11019/100000 [3:18:32<14:28:33,  1.71it/s]
Train steps ... :  11%|█         | 11020/100000 [3:18:33<14:28:41,  1.71it/s]
Train steps ... :  11%|���         | 11021/100000 [3:18:33<14:28:14,  1.71it/s]
Train steps ... :  11%|█         | 11022/100000 [3:18:34<14:28:40,  1.71it/s]
Train steps ... :  11%|█         | 11023/100000 [3:18:34<14:28:22,  1.71it/s]
Train steps ... :  11%|█         | 11024/100000 [3:18:35<14:30:02,  1.70it/s]
Train steps ... :  11%|█         | 11025/100000 [3:18:35<14:27:04,  1.71it/s]Step... (11025 / 100000 | Loss: 0.9358621835708618, Learning Rate: 8.942211055276383e-05)
+
                                                                             
Step... (11025 / 100000 | Loss: 1.302675724029541, Learning Rate: 8.942211055276383e-05)
+
Train steps ... :  11%|█         | 11025/100000 [3:18:36<14:27:04,  1.71it/s]
Train steps ... :  11%|█         | 11026/100000 [3:18:36<14:27:50,  1.71it/s]
Train steps ... :  11%|█         | 11027/100000 [3:18:37<14:27:59,  1.71it/s]
Train steps ... :  11%|█         | 11028/100000 [3:18:37<14:26:11,  1.71it/s]
Train steps ... :  11%|█         | 11029/100000 [3:18:38<14:26:27,  1.71it/s]
Train steps ... :  11%|█         | 11030/100000 [3:18:38<14:28:51,  1.71it/s]
Train steps ... :  11%|█         | 11031/100000 [3:18:39<14:26:34,  1.71it/s]
Train steps ... :  11%|█         | 11032/100000 [3:18:40<14:29:23,  1.71it/s]
Train steps ... :  11%|█         | 11033/100000 [3:18:40<14:29:23,  1.71it/s]
Train steps ... :  11%|█         | 11034/100000 [3:18:41<14:27:57,  1.71it/s]
Train steps ... :  11%|█         | 11035/100000 [3:18:41<14:28:14,  1.71it/s]
Train steps ... :  11%|█         | 11036/100000 [3:18:42<14:26:49,  1.71it/s]
Train steps ... :  11%|█         | 11037/100000 [3:18:42<14:27:05,  1.71it/s]
Train steps ... :  11%|█         | 11038/100000 [3:18:43<14:28:19,  1.71it/s]
Train steps ... :  11%|█         | 11039/100000 [3:18:44<14:27:22,  1.71it/s]
Train steps ... :  11%|█         | 11040/100000 [3:18:44<14:28:34,  1.71it/s]
Train steps ... :  11%|█         | 11041/100000 [3:18:45<14:28:28,  1.71it/s]
Train steps ... :  11%|█         | 11042/100000 [3:18:45<14:29:27,  1.71it/s]
Train steps ... :  11%|█         | 11043/100000 [3:18:46<14:26:47,  1.71it/s]
Train steps ... :  11%|█         | 11044/100000 [3:18:47<14:27:51,  1.71it/s]
Train steps ... :  11%|█         | 11045/100000 [3:18:47<14:27:31,  1.71it/s]
Train steps ... :  11%|█         | 11046/100000 [3:18:48<14:26:30,  1.71it/s]
Train steps ... :  11%|█         | 11047/100000 [3:18:48<14:26:58,  1.71it/s]
Train steps ... :  11%|█         | 11048/100000 [3:18:49<14:26:17,  1.71it/s]
Train steps ... :  11%|█         | 11049/100000 [3:18:50<14:26:51,  1.71it/s]
Train steps ... :  11%|█         | 11050/100000 [3:18:50<14:26:31,  1.71it/s]Step... (11050 / 100000 | Loss: 1.0823936462402344, Learning Rate: 8.939698492462311e-05)
+
                                                                             
Step... (11050 / 100000 | Loss: 1.3075133562088013, Learning Rate: 8.939698492462311e-05)
+
Train steps ... :  11%|█         | 11050/100000 [3:18:50<14:26:31,  1.71it/s]
Train steps ... :  11%|█         | 11051/100000 [3:18:51<14:26:43,  1.71it/s]
Train steps ... :  11%|█         | 11052/100000 [3:18:51<14:26:39,  1.71it/s]
Train steps ... :  11%|█         | 11053/100000 [3:18:52<14:26:35,  1.71it/s]
Train steps ... :  11%|█         | 11054/100000 [3:18:52<14:26:33,  1.71it/s]
Train steps ... :  11%|█         | 11055/100000 [3:18:53<14:26:57,  1.71it/s]
Train steps ... :  11%|█         | 11056/100000 [3:18:54<14:30:22,  1.70it/s]
Train steps ... :  11%|█         | 11057/100000 [3:18:54<14:26:32,  1.71it/s]
Train steps ... :  11%|█         | 11058/100000 [3:18:55<14:29:05,  1.71it/s]
Train steps ... :  11%|█         | 11059/100000 [3:18:55<14:28:43,  1.71it/s]
Train steps ... :  11%|█         | 11060/100000 [3:18:56<14:28:54,  1.71it/s]
Train steps ... :  11%|█         | 11061/100000 [3:18:57<14:27:37,  1.71it/s]
Train steps ... :  11%|█         | 11062/100000 [3:18:57<14:28:35,  1.71it/s]
Train steps ... :  11%|█         | 11063/100000 [3:18:58<14:27:19,  1.71it/s]
Train steps ... :  11%|█         | 11064/100000 [3:18:58<14:27:15,  1.71it/s]
Train steps ... :  11%|█         | 11065/100000 [3:18:59<14:26:31,  1.71it/s]
Train steps ... :  11%|█         | 11066/100000 [3:18:59<14:25:37,  1.71it/s]
Train steps ... :  11%|█         | 11067/100000 [3:19:00<14:25:35,  1.71it/s]
Train steps ... :  11%|█         | 11068/100000 [3:19:01<14:25:57,  1.71it/s]
Train steps ... :  11%|█         | 11069/100000 [3:19:01<14:25:41,  1.71it/s]
Train steps ... :  11%|█         | 11070/100000 [3:19:02<14:25:46,  1.71it/s]
Train steps ... :  11%|█         | 11071/100000 [3:19:02<14:26:11,  1.71it/s]
Train steps ... :  11%|█         | 11072/100000 [3:19:03<14:25:18,  1.71it/s]
Train steps ... :  11%|█         | 11073/100000 [3:19:04<14:27:03,  1.71it/s]
Train steps ... :  11%|█         | 11074/100000 [3:19:04<14:27:13,  1.71it/s]
Train steps ... :  11%|█         | 11075/100000 [3:19:05<14:26:12,  1.71it/s]Step... (11075 / 100000 | Loss: 1.477747917175293, Learning Rate: 8.937185929648242e-05)
+
                                                                             
Step... (11075 / 100000 | Loss: 1.0317621231079102, Learning Rate: 8.937185929648242e-05)
+
Train steps ... :  11%|█         | 11075/100000 [3:19:05<14:26:12,  1.71it/s]
Train steps ... :  11%|█         | 11076/100000 [3:19:05<14:26:01,  1.71it/s]
Train steps ... :  11%|█         | 11077/100000 [3:19:06<14:26:01,  1.71it/s]
Train steps ... :  11%|█         | 11078/100000 [3:19:06<14:25:37,  1.71it/s]
Train steps ... :  11%|█         | 11079/100000 [3:19:07<14:24:54,  1.71it/s]
Train steps ... :  11%|█         | 11080/100000 [3:19:08<14:26:13,  1.71it/s]
Train steps ... :  11%|█         | 11081/100000 [3:19:08<14:25:11,  1.71it/s]
Train steps ... :  11%|█         | 11082/100000 [3:19:09<14:25:52,  1.71it/s]
Train steps ... :  11%|█         | 11083/100000 [3:19:09<14:25:12,  1.71it/s]
Train steps ... :  11%|█         | 11084/100000 [3:19:10<14:24:38,  1.71it/s]
Train steps ... :  11%|█         | 11085/100000 [3:19:11<14:24:44,  1.71it/s]
Train steps ... :  11%|█         | 11086/100000 [3:19:11<14:24:47,  1.71it/s]
Train steps ... :  11%|█         | 11087/100000 [3:19:12<14:25:22,  1.71it/s]
Train steps ... :  11%|█         | 11088/100000 [3:19:12<14:25:45,  1.71it/s]
Train steps ... :  11%|█         | 11089/100000 [3:19:13<14:26:24,  1.71it/s]
Train steps ... :  11%|█         | 11090/100000 [3:19:13<14:25:48,  1.71it/s]
Train steps ... :  11%|█         | 11091/100000 [3:19:14<14:26:01,  1.71it/s]
Train steps ... :  11%|█         | 11092/100000 [3:19:15<14:28:44,  1.71it/s]
Train steps ... :  11%|█         | 11093/100000 [3:19:15<14:26:35,  1.71it/s]
Train steps ... :  11%|█         | 11094/100000 [3:19:16<14:26:57,  1.71it/s]
Train steps ... :  11%|█         | 11095/100000 [3:19:16<14:26:30,  1.71it/s]
Train steps ... :  11%|█         | 11096/100000 [3:19:17<14:25:51,  1.71it/s]
Train steps ... :  11%|█         | 11097/100000 [3:19:18<14:26:08,  1.71it/s]
Train steps ... :  11%|█         | 11098/100000 [3:19:18<14:25:28,  1.71it/s]
Train steps ... :  11%|█         | 11099/100000 [3:19:19<14:24:47,  1.71it/s]
Train steps ... :  11%|█         | 11100/100000 [3:19:19<14:25:16,  1.71it/s]Step... (11100 / 100000 | Loss: 1.2680253982543945, Learning Rate: 8.93467336683417e-05)
+
                                                                             
Step... (11100 / 100000 | Loss: 1.2421252727508545, Learning Rate: 8.93467336683417e-05)
+
Train steps ... :  11%|█         | 11100/100000 [3:19:20<14:25:16,  1.71it/s]
Train steps ... :  11%|█         | 11101/100000 [3:19:20<14:25:01,  1.71it/s]
Train steps ... :  11%|█         | 11102/100000 [3:19:20<14:24:53,  1.71it/s]
Train steps ... :  11%|█         | 11103/100000 [3:19:21<14:25:31,  1.71it/s]
Train steps ... :  11%|█         | 11104/100000 [3:19:22<14:25:11,  1.71it/s]
Train steps ... :  11%|█         | 11105/100000 [3:19:22<14:25:25,  1.71it/s]
Train steps ... :  11%|█         | 11106/100000 [3:19:23<14:26:41,  1.71it/s]
Train steps ... :  11%|█         | 11107/100000 [3:19:23<14:26:37,  1.71it/s]
Train steps ... :  11%|█         | 11108/100000 [3:19:24<14:27:17,  1.71it/s]
Train steps ... :  11%|█         | 11109/100000 [3:19:25<14:26:34,  1.71it/s]
Train steps ... :  11%|█         | 11110/100000 [3:19:25<14:26:43,  1.71it/s]
Train steps ... :  11%|█         | 11111/100000 [3:19:26<14:26:50,  1.71it/s]
Train steps ... :  11%|█         | 11112/100000 [3:19:26<14:26:57,  1.71it/s]
Train steps ... :  11%|█         | 11113/100000 [3:19:27<14:26:46,  1.71it/s]
Train steps ... :  11%|█         | 11114/100000 [3:19:28<14:25:50,  1.71it/s]
Train steps ... :  11%|█         | 11115/100000 [3:19:28<14:25:35,  1.71it/s]
Train steps ... :  11%|█         | 11116/100000 [3:19:29<14:25:41,  1.71it/s]
Train steps ... :  11%|█         | 11117/100000 [3:19:29<14:26:02,  1.71it/s]
Train steps ... :  11%|█         | 11118/100000 [3:19:30<14:26:25,  1.71it/s]
Train steps ... :  11%|█         | 11119/100000 [3:19:30<14:27:20,  1.71it/s]
Train steps ... :  11%|█         | 11120/100000 [3:19:31<14:27:05,  1.71it/s]
Train steps ... :  11%|█         | 11121/100000 [3:19:32<14:26:01,  1.71it/s]
Train steps ... :  11%|█         | 11122/100000 [3:19:32<14:26:09,  1.71it/s]
Train steps ... :  11%|█         | 11123/100000 [3:19:33<14:25:22,  1.71it/s]
Train steps ... :  11%|█         | 11124/100000 [3:19:33<14:25:04,  1.71it/s]
Train steps ... :  11%|█         | 11125/100000 [3:19:34<14:25:47,  1.71it/s]Step... (11125 / 100000 | Loss: 2.173628330230713, Learning Rate: 8.932160804020101e-05)
+
                                                                             
Step... (11125 / 100000 | Loss: 1.2516531944274902, Learning Rate: 8.932160804020101e-05)
+
Train steps ... :  11%|█         | 11125/100000 [3:19:34<14:25:47,  1.71it/s]
Train steps ... :  11%|█         | 11126/100000 [3:19:35<14:26:07,  1.71it/s]
Train steps ... :  11%|█         | 11127/100000 [3:19:35<14:25:25,  1.71it/s]
Train steps ... :  11%|█         | 11128/100000 [3:19:36<14:25:57,  1.71it/s]
Train steps ... :  11%|█         | 11129/100000 [3:19:36<14:26:43,  1.71it/s]
Train steps ... :  11%|█         | 11130/100000 [3:19:37<14:25:41,  1.71it/s]
Train steps ... :  11%|█         | 11131/100000 [3:19:37<14:25:45,  1.71it/s]
Train steps ... :  11%|█         | 11132/100000 [3:19:38<14:25:11,  1.71it/s]
Train steps ... :  11%|█         | 11133/100000 [3:19:39<14:25:30,  1.71it/s]
Train steps ... :  11%|█         | 11134/100000 [3:19:39<14:26:03,  1.71it/s]
Train steps ... :  11%|█         | 11135/100000 [3:19:40<14:25:07,  1.71it/s]
Train steps ... :  11%|█         | 11136/100000 [3:19:40<14:25:18,  1.71it/s]
Train steps ... :  11%|█         | 11137/100000 [3:19:41<14:26:18,  1.71it/s]
Train steps ... :  11%|█         | 11138/100000 [3:19:42<14:25:21,  1.71it/s]
Train steps ... :  11%|█         | 11139/100000 [3:19:42<14:25:51,  1.71it/s]
Train steps ... :  11%|█         | 11140/100000 [3:19:43<14:25:52,  1.71it/s]
Train steps ... :  11%|█         | 11141/100000 [3:19:43<14:25:38,  1.71it/s]
Train steps ... :  11%|█         | 11142/100000 [3:19:44<14:25:08,  1.71it/s]
Train steps ... :  11%|█         | 11143/100000 [3:19:44<14:25:55,  1.71it/s]
Train steps ... :  11%|█         | 11144/100000 [3:19:45<14:26:10,  1.71it/s]
Train steps ... :  11%|█         | 11145/100000 [3:19:46<14:26:26,  1.71it/s]
Train steps ... :  11%|█         | 11146/100000 [3:19:46<14:25:35,  1.71it/s]
Train steps ... :  11%|█         | 11147/100000 [3:19:47<14:25:18,  1.71it/s]
Train steps ... :  11%|█         | 11148/100000 [3:19:47<14:26:33,  1.71it/s]
Train steps ... :  11%|█         | 11149/100000 [3:19:48<14:25:49,  1.71it/s]
Train steps ... :  11%|█         | 11150/100000 [3:19:49<14:25:19,  1.71it/s]Step... (11150 / 100000 | Loss: 1.2109363079071045, Learning Rate: 8.92964824120603e-05)
+
                                                                             
Step... (11150 / 100000 | Loss: 1.576911211013794, Learning Rate: 8.92964824120603e-05)
+
Train steps ... :  11%|█         | 11150/100000 [3:19:49<14:25:19,  1.71it/s]
Train steps ... :  11%|█         | 11151/100000 [3:19:49<14:25:46,  1.71it/s]
Train steps ... :  11%|█         | 11152/100000 [3:19:50<14:27:41,  1.71it/s]
Train steps ... :  11%|█         | 11153/100000 [3:19:50<14:27:05,  1.71it/s]
Train steps ... :  11%|█         | 11154/100000 [3:19:51<14:26:13,  1.71it/s]
Train steps ... :  11%|█         | 11155/100000 [3:19:51<14:24:57,  1.71it/s]
Train steps ... :  11%|█         | 11156/100000 [3:19:52<14:27:12,  1.71it/s]
Train steps ... :  11%|█         | 11157/100000 [3:19:53<14:26:47,  1.71it/s]
Train steps ... :  11%|█         | 11158/100000 [3:19:53<14:26:54,  1.71it/s]
Train steps ... :  11%|█         | 11159/100000 [3:19:54<14:25:58,  1.71it/s]
Train steps ... :  11%|█         | 11160/100000 [3:19:54<14:26:09,  1.71it/s]
Train steps ... :  11%|█         | 11161/100000 [3:19:55<14:25:41,  1.71it/s]
Train steps ... :  11%|█         | 11162/100000 [3:19:56<14:25:21,  1.71it/s]
Train steps ... :  11%|█         | 11163/100000 [3:19:56<14:26:14,  1.71it/s]
Train steps ... :  11%|█         | 11164/100000 [3:19:57<14:26:40,  1.71it/s]
Train steps ... :  11%|█         | 11165/100000 [3:19:57<14:25:53,  1.71it/s]
Train steps ... :  11%|█         | 11166/100000 [3:19:58<14:25:23,  1.71it/s]
Train steps ... :  11%|█         | 11167/100000 [3:19:58<14:25:02,  1.71it/s]
Train steps ... :  11%|█         | 11168/100000 [3:19:59<14:24:46,  1.71it/s]
Train steps ... :  11%|█         | 11169/100000 [3:20:00<14:24:55,  1.71it/s]
Train steps ... :  11%|█         | 11170/100000 [3:20:00<14:25:27,  1.71it/s]
Train steps ... :  11%|█         | 11171/100000 [3:20:01<14:25:17,  1.71it/s]
Train steps ... :  11%|█         | 11172/100000 [3:20:01<14:24:58,  1.71it/s]
Train steps ... :  11%|█         | 11173/100000 [3:20:02<14:24:37,  1.71it/s]
Train steps ... :  11%|█         | 11174/100000 [3:20:03<14:25:27,  1.71it/s]
Train steps ... :  11%|█         | 11175/100000 [3:20:03<14:25:06,  1.71it/s]Step... (11175 / 100000 | Loss: 1.031308650970459, Learning Rate: 8.927135678391961e-05)
+
                                                                             
Step... (11175 / 100000 | Loss: 1.4298624992370605, Learning Rate: 8.927135678391961e-05)
+
Train steps ... :  11%|█         | 11175/100000 [3:20:03<14:25:06,  1.71it/s]
Train steps ... :  11%|█         | 11176/100000 [3:20:04<14:25:16,  1.71it/s]
Train steps ... :  11%|█         | 11177/100000 [3:20:04<14:25:00,  1.71it/s]
Train steps ... :  11%|█         | 11178/100000 [3:20:05<14:24:10,  1.71it/s]
Train steps ... :  11%|█         | 11179/100000 [3:20:06<14:24:33,  1.71it/s]
Train steps ... :  11%|█         | 11180/100000 [3:20:06<14:25:24,  1.71it/s]
Train steps ... :  11%|█         | 11181/100000 [3:20:07<14:26:27,  1.71it/s]
Train steps ... :  11%|█         | 11182/100000 [3:20:07<14:25:28,  1.71it/s]
Train steps ... :  11%|█         | 11183/100000 [3:20:08<14:26:35,  1.71it/s]
Train steps ... :  11%|█         | 11184/100000 [3:20:08<14:26:15,  1.71it/s]
Train steps ... :  11%|█         | 11185/100000 [3:20:09<14:26:21,  1.71it/s]
Train steps ... :  11%|█         | 11186/100000 [3:20:10<14:26:05,  1.71it/s]
Train steps ... :  11%|█         | 11187/100000 [3:20:10<14:26:05,  1.71it/s]
Train steps ... :  11%|█         | 11188/100000 [3:20:11<14:25:46,  1.71it/s]
Train steps ... :  11%|█         | 11189/100000 [3:20:11<14:24:48,  1.71it/s]
Train steps ... :  11%|█         | 11190/100000 [3:20:12<14:24:05,  1.71it/s]
Train steps ... :  11%|█         | 11191/100000 [3:20:13<14:24:06,  1.71it/s]
Train steps ... :  11%|█         | 11192/100000 [3:20:13<14:24:33,  1.71it/s]
Train steps ... :  11%|█         | 11193/100000 [3:20:14<14:24:19,  1.71it/s]
Train steps ... :  11%|█         | 11194/100000 [3:20:14<14:23:54,  1.71it/s]
Train steps ... :  11%|█         | 11195/100000 [3:20:15<14:24:09,  1.71it/s]
Train steps ... :  11%|█         | 11196/100000 [3:20:15<14:24:59,  1.71it/s]
Train steps ... :  11%|█         | 11197/100000 [3:20:16<14:24:41,  1.71it/s]
Train steps ... :  11%|█         | 11198/100000 [3:20:17<14:24:29,  1.71it/s]
Train steps ... :  11%|█         | 11199/100000 [3:20:17<14:24:34,  1.71it/s]
Train steps ... :  11%|█         | 11200/100000 [3:20:18<14:23:57,  1.71it/s]Step... (11200 / 100000 | Loss: 1.1348707675933838, Learning Rate: 8.92462311557789e-05)
+
                                                                             
Step... (11200 / 100000 | Loss: 1.3187754154205322, Learning Rate: 8.92462311557789e-05)
+
Train steps ... :  11%|█         | 11200/100000 [3:20:18<14:23:57,  1.71it/s]
Train steps ... :  11%|█         | 11201/100000 [3:20:18<14:24:53,  1.71it/s]
Train steps ... :  11%|█         | 11202/100000 [3:20:19<14:24:11,  1.71it/s]
Train steps ... :  11%|█         | 11203/100000 [3:20:20<14:24:20,  1.71it/s]
Train steps ... :  11%|█         | 11204/100000 [3:20:20<14:25:04,  1.71it/s]
Train steps ... :  11%|█         | 11205/100000 [3:20:21<14:24:11,  1.71it/s]
Train steps ... :  11%|█         | 11206/100000 [3:20:21<14:24:16,  1.71it/s]
Train steps ... :  11%|█         | 11207/100000 [3:20:22<14:24:23,  1.71it/s]
Train steps ... :  11%|█         | 11208/100000 [3:20:22<14:25:00,  1.71it/s]
Train steps ... :  11%|█         | 11209/100000 [3:20:23<14:25:10,  1.71it/s]
Train steps ... :  11%|█         | 11210/100000 [3:20:24<14:24:48,  1.71it/s]
Train steps ... :  11%|█         | 11211/100000 [3:20:24<14:24:42,  1.71it/s]
Train steps ... :  11%|█         | 11212/100000 [3:20:25<14:24:03,  1.71it/s]
Train steps ... :  11%|█         | 11213/100000 [3:20:25<14:23:44,  1.71it/s]
Train steps ... :  11%|█         | 11214/100000 [3:20:26<14:23:56,  1.71it/s]
Train steps ... :  11%|█         | 11215/100000 [3:20:27<14:24:35,  1.71it/s]
Train steps ... :  11%|█         | 11216/100000 [3:20:27<14:24:08,  1.71it/s]
Train steps ... :  11%|█         | 11217/100000 [3:20:28<14:24:00,  1.71it/s]
Train steps ... :  11%|█         | 11218/100000 [3:20:28<14:24:31,  1.71it/s]
Train steps ... :  11%|█         | 11219/100000 [3:20:29<14:24:06,  1.71it/s]
Train steps ... :  11%|█         | 11220/100000 [3:20:29<14:23:41,  1.71it/s]
Train steps ... :  11%|█         | 11221/100000 [3:20:30<14:23:54,  1.71it/s]
Train steps ... :  11%|█         | 11222/100000 [3:20:31<14:24:15,  1.71it/s]
Train steps ... :  11%|█         | 11223/100000 [3:20:31<14:23:49,  1.71it/s]
Train steps ... :  11%|█         | 11224/100000 [3:20:32<14:24:44,  1.71it/s]
Train steps ... :  11%|█         | 11225/100000 [3:20:32<14:24:17,  1.71it/s]Step... (11225 / 100000 | Loss: 1.099244236946106, Learning Rate: 8.922110552763819e-05)
+
                                                                             
Step... (11225 / 100000 | Loss: 1.2263126373291016, Learning Rate: 8.922110552763819e-05)
+
Train steps ... :  11%|█         | 11225/100000 [3:20:33<14:24:17,  1.71it/s]
Train steps ... :  11%|█         | 11226/100000 [3:20:33<14:24:34,  1.71it/s]
Train steps ... :  11%|█         | 11227/100000 [3:20:34<14:25:18,  1.71it/s]
Train steps ... :  11%|█         | 11228/100000 [3:20:34<14:25:28,  1.71it/s]
Train steps ... :  11%|█         | 11229/100000 [3:20:35<14:25:22,  1.71it/s]
Train steps ... :  11%|█         | 11230/100000 [3:20:35<14:26:27,  1.71it/s]
Train steps ... :  11%|█         | 11231/100000 [3:20:36<14:26:07,  1.71it/s]
Train steps ... :  11%|█         | 11232/100000 [3:20:36<14:26:16,  1.71it/s]
Train steps ... :  11%|█         | 11233/100000 [3:20:37<14:25:53,  1.71it/s]
Train steps ... :  11%|█         | 11234/100000 [3:20:38<14:24:36,  1.71it/s]
Train steps ... :  11%|█         | 11235/100000 [3:20:38<14:24:20,  1.71it/s]
Train steps ... :  11%|█         | 11236/100000 [3:20:39<14:24:48,  1.71it/s]
Train steps ... :  11%|█         | 11237/100000 [3:20:39<14:24:39,  1.71it/s]
Train steps ... :  11%|█         | 11238/100000 [3:20:40<14:24:12,  1.71it/s]
Train steps ... :  11%|█         | 11239/100000 [3:20:41<14:24:37,  1.71it/s]
Train steps ... :  11%|█         | 11240/100000 [3:20:41<14:24:04,  1.71it/s]
Train steps ... :  11%|█         | 11241/100000 [3:20:42<14:24:47,  1.71it/s]
Train steps ... :  11%|█         | 11242/100000 [3:20:42<14:24:38,  1.71it/s]
Train steps ... :  11%|█         | 11243/100000 [3:20:43<14:24:20,  1.71it/s]
Train steps ... :  11%|█         | 11244/100000 [3:20:43<14:26:02,  1.71it/s]
Train steps ... :  11%|█         | 11245/100000 [3:20:44<14:26:11,  1.71it/s]
Train steps ... :  11%|█         | 11246/100000 [3:20:45<14:25:38,  1.71it/s]
Train steps ... :  11%|█         | 11247/100000 [3:20:45<14:25:00,  1.71it/s]
Train steps ... :  11%|█         | 11248/100000 [3:20:46<14:26:26,  1.71it/s]
Train steps ... :  11%|█         | 11249/100000 [3:20:46<14:25:37,  1.71it/s]
Train steps ... :  11%|█▏        | 11250/100000 [3:20:47<14:24:57,  1.71it/s]Step... (11250 / 100000 | Loss: 1.0473601818084717, Learning Rate: 8.91959798994975e-05)
+
                                                                             
Step... (11250 / 100000 | Loss: 1.321505069732666, Learning Rate: 8.91959798994975e-05)
+
Train steps ... :  11%|█▏        | 11250/100000 [3:20:47<14:24:57,  1.71it/s]
Train steps ... :  11%|█▏        | 11251/100000 [3:20:48<14:24:59,  1.71it/s]
Train steps ... :  11%|█▏        | 11252/100000 [3:20:48<14:24:01,  1.71it/s]
Train steps ... :  11%|█▏        | 11253/100000 [3:20:49<14:24:53,  1.71it/s]
Train steps ... :  11%|█▏        | 11254/100000 [3:20:49<14:24:05,  1.71it/s]
Train steps ... :  11%|█▏        | 11255/100000 [3:20:50<14:23:59,  1.71it/s]
Train steps ... :  11%|█▏        | 11256/100000 [3:20:51<14:23:30,  1.71it/s]
Train steps ... :  11%|█▏        | 11257/100000 [3:20:51<14:23:38,  1.71it/s]
Train steps ... :  11%|█▏        | 11258/100000 [3:20:52<14:24:00,  1.71it/s]
Train steps ... :  11%|█▏        | 11259/100000 [3:20:52<14:24:16,  1.71it/s]
Train steps ... :  11%|█▏        | 11260/100000 [3:20:53<14:24:11,  1.71it/s]
Train steps ... :  11%|█▏        | 11261/100000 [3:20:53<14:26:33,  1.71it/s]
Train steps ... :  11%|█▏        | 11262/100000 [3:20:54<14:24:22,  1.71it/s]
Train steps ... :  11%|█▏        | 11263/100000 [3:20:55<14:23:29,  1.71it/s]
Train steps ... :  11%|█▏        | 11264/100000 [3:20:55<14:23:29,  1.71it/s]
Train steps ... :  11%|█▏        | 11265/100000 [3:20:56<14:23:17,  1.71it/s]
Train steps ... :  11%|█▏        | 11266/100000 [3:20:56<14:23:21,  1.71it/s]
Train steps ... :  11%|█▏        | 11267/100000 [3:20:57<14:24:10,  1.71it/s]
Train steps ... :  11%|█▏        | 11268/100000 [3:20:58<14:24:10,  1.71it/s]
Train steps ... :  11%|█▏        | 11269/100000 [3:20:58<14:23:58,  1.71it/s]
Train steps ... :  11%|█▏        | 11270/100000 [3:20:59<14:24:01,  1.71it/s]
Train steps ... :  11%|█▏        | 11271/100000 [3:20:59<14:23:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11272/100000 [3:21:00<14:23:04,  1.71it/s]
Train steps ... :  11%|█▏        | 11273/100000 [3:21:00<14:23:11,  1.71it/s]
Train steps ... :  11%|█▏        | 11274/100000 [3:21:01<14:23:38,  1.71it/s]
Train steps ... :  11%|█▏        | 11275/100000 [3:21:02<14:23:07,  1.71it/s]Step... (11275 / 100000 | Loss: 1.1253223419189453, Learning Rate: 8.917085427135678e-05)
+
                                                                             
Step... (11275 / 100000 | Loss: 1.136976718902588, Learning Rate: 8.917085427135678e-05)
+
Train steps ... :  11%|█▏        | 11275/100000 [3:21:02<14:23:07,  1.71it/s]
Train steps ... :  11%|█▏        | 11276/100000 [3:21:02<14:23:16,  1.71it/s]
Train steps ... :  11%|█▏        | 11277/100000 [3:21:03<14:22:42,  1.71it/s]
Train steps ... :  11%|█▏        | 11278/100000 [3:21:03<14:23:06,  1.71it/s]
Train steps ... :  11%|█▏        | 11279/100000 [3:21:04<14:24:16,  1.71it/s]
Train steps ... :  11%|█▏        | 11280/100000 [3:21:05<14:23:51,  1.71it/s]
Train steps ... :  11%|█▏        | 11281/100000 [3:21:05<14:25:03,  1.71it/s]
Train steps ... :  11%|█▏        | 11282/100000 [3:21:06<14:24:43,  1.71it/s]
Train steps ... :  11%|█▏        | 11283/100000 [3:21:06<14:25:07,  1.71it/s]
Train steps ... :  11%|█▏        | 11284/100000 [3:21:07<14:25:00,  1.71it/s]
Train steps ... :  11%|█▏        | 11285/100000 [3:21:07<14:24:27,  1.71it/s]
Train steps ... :  11%|█▏        | 11286/100000 [3:21:08<14:25:23,  1.71it/s]
Train steps ... :  11%|█▏        | 11287/100000 [3:21:09<14:24:38,  1.71it/s]
Train steps ... :  11%|█▏        | 11288/100000 [3:21:09<14:24:01,  1.71it/s]
Train steps ... :  11%|█▏        | 11289/100000 [3:21:10<14:23:38,  1.71it/s]
Train steps ... :  11%|█▏        | 11290/100000 [3:21:10<14:23:12,  1.71it/s]
Train steps ... :  11%|█▏        | 11291/100000 [3:21:11<14:24:11,  1.71it/s]
Train steps ... :  11%|█▏        | 11292/100000 [3:21:12<14:23:40,  1.71it/s]
Train steps ... :  11%|█▏        | 11293/100000 [3:21:12<14:23:33,  1.71it/s]
Train steps ... :  11%|█▏        | 11294/100000 [3:21:13<14:26:04,  1.71it/s]
Train steps ... :  11%|█▏        | 11295/100000 [3:21:13<14:23:32,  1.71it/s]
Train steps ... :  11%|█▏        | 11296/100000 [3:21:14<14:24:40,  1.71it/s]
Train steps ... :  11%|█▏        | 11297/100000 [3:21:14<14:24:51,  1.71it/s]
Train steps ... :  11%|█▏        | 11298/100000 [3:21:15<14:23:43,  1.71it/s]
Train steps ... :  11%|█▏        | 11299/100000 [3:21:16<14:24:21,  1.71it/s]
Train steps ... :  11%|█▏        | 11300/100000 [3:21:16<14:24:00,  1.71it/s]Step... (11300 / 100000 | Loss: 1.2890164852142334, Learning Rate: 8.914572864321609e-05)
+
                                                                             
Step... (11300 / 100000 | Loss: 1.0268080234527588, Learning Rate: 8.914572864321609e-05)
+
Train steps ... :  11%|█▏        | 11300/100000 [3:21:17<14:24:00,  1.71it/s]
Train steps ... :  11%|█▏        | 11301/100000 [3:21:17<14:24:02,  1.71it/s]
Train steps ... :  11%|█▏        | 11302/100000 [3:21:17<14:24:31,  1.71it/s]
Train steps ... :  11%|█▏        | 11303/100000 [3:21:18<14:26:44,  1.71it/s]
Train steps ... :  11%|█▏        | 11304/100000 [3:21:19<14:25:53,  1.71it/s]
Train steps ... :  11%|█▏        | 11305/100000 [3:21:19<14:25:40,  1.71it/s]
Train steps ... :  11%|█▏        | 11306/100000 [3:21:20<14:25:32,  1.71it/s]
Train steps ... :  11%|█▏        | 11307/100000 [3:21:20<14:24:23,  1.71it/s]
Train steps ... :  11%|█▏        | 11308/100000 [3:21:21<14:24:11,  1.71it/s]
Train steps ... :  11%|█▏        | 11309/100000 [3:21:21<14:23:43,  1.71it/s]
Train steps ... :  11%|█▏        | 11310/100000 [3:21:22<14:23:47,  1.71it/s]
Train steps ... :  11%|█▏        | 11311/100000 [3:21:23<14:23:50,  1.71it/s]
Train steps ... :  11%|█▏        | 11312/100000 [3:21:23<14:23:57,  1.71it/s]
Train steps ... :  11%|█▏        | 11313/100000 [3:21:24<14:23:28,  1.71it/s]
Train steps ... :  11%|█▏        | 11314/100000 [3:21:24<14:23:31,  1.71it/s]
Train steps ... :  11%|█▏        | 11315/100000 [3:21:25<14:24:24,  1.71it/s]
Train steps ... :  11%|█▏        | 11316/100000 [3:21:26<14:24:47,  1.71it/s]
Train steps ... :  11%|█▏        | 11317/100000 [3:21:26<14:24:17,  1.71it/s]
Train steps ... :  11%|█▏        | 11318/100000 [3:21:27<14:23:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11319/100000 [3:21:27<14:23:50,  1.71it/s]
Train steps ... :  11%|█▏        | 11320/100000 [3:21:28<14:23:17,  1.71it/s]
Train steps ... :  11%|█▏        | 11321/100000 [3:21:28<14:23:29,  1.71it/s]
Train steps ... :  11%|█▏        | 11322/100000 [3:21:29<14:23:15,  1.71it/s]
Train steps ... :  11%|█▏        | 11323/100000 [3:21:30<14:23:23,  1.71it/s]
Train steps ... :  11%|█▏        | 11324/100000 [3:21:30<14:23:27,  1.71it/s]
Train steps ... :  11%|█▏        | 11325/100000 [3:21:31<14:22:50,  1.71it/s]Step... (11325 / 100000 | Loss: 1.3678957223892212, Learning Rate: 8.912060301507537e-05)
+
                                                                             
Step... (11325 / 100000 | Loss: 1.3214104175567627, Learning Rate: 8.912060301507537e-05)
+
Train steps ... :  11%|█▏        | 11325/100000 [3:21:31<14:22:50,  1.71it/s]
Train steps ... :  11%|█▏        | 11326/100000 [3:21:31<14:24:05,  1.71it/s]
Train steps ... :  11%|█▏        | 11327/100000 [3:21:32<14:23:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11328/100000 [3:21:33<14:23:57,  1.71it/s]
Train steps ... :  11%|█▏        | 11329/100000 [3:21:33<14:23:48,  1.71it/s]
Train steps ... :  11%|█▏        | 11330/100000 [3:21:34<14:23:22,  1.71it/s]
Train steps ... :  11%|█▏        | 11331/100000 [3:21:34<14:23:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11332/100000 [3:21:35<14:23:36,  1.71it/s]
Train steps ... :  11%|█▏        | 11333/100000 [3:21:36<14:23:11,  1.71it/s]
Train steps ... :  11%|█▏        | 11334/100000 [3:21:36<14:23:58,  1.71it/s]
Train steps ... :  11%|█▏        | 11335/100000 [3:21:37<14:24:53,  1.71it/s]
Train steps ... :  11%|█▏        | 11336/100000 [3:21:37<14:24:55,  1.71it/s]
Train steps ... :  11%|█▏        | 11337/100000 [3:21:38<14:24:00,  1.71it/s]
Train steps ... :  11%|█▏        | 11338/100000 [3:21:38<14:23:47,  1.71it/s]
Train steps ... :  11%|█▏        | 11339/100000 [3:21:39<14:23:43,  1.71it/s]
Train steps ... :  11%|█▏        | 11340/100000 [3:21:40<14:23:30,  1.71it/s]
Train steps ... :  11%|█▏        | 11341/100000 [3:21:40<14:23:12,  1.71it/s]
Train steps ... :  11%|█▏        | 11342/100000 [3:21:41<14:23:49,  1.71it/s]
Train steps ... :  11%|█▏        | 11343/100000 [3:21:41<14:26:25,  1.71it/s]
Train steps ... :  11%|█▏        | 11344/100000 [3:21:42<14:22:48,  1.71it/s]
Train steps ... :  11%|█▏        | 11345/100000 [3:21:43<14:23:26,  1.71it/s]
Train steps ... :  11%|█▏        | 11346/100000 [3:21:43<14:22:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11347/100000 [3:21:44<14:22:37,  1.71it/s]
Train steps ... :  11%|█▏        | 11348/100000 [3:21:44<14:22:18,  1.71it/s]
Train steps ... :  11%|█▏        | 11349/100000 [3:21:45<14:23:08,  1.71it/s]
Train steps ... :  11%|█▏        | 11350/100000 [3:21:45<14:23:50,  1.71it/s]Step... (11350 / 100000 | Loss: 1.841856598854065, Learning Rate: 8.909547738693468e-05)
+
                                                                             
Step... (11350 / 100000 | Loss: 1.397670030593872, Learning Rate: 8.909547738693468e-05)
+
Train steps ... :  11%|█▏        | 11350/100000 [3:21:46<14:23:50,  1.71it/s]
Train steps ... :  11%|█▏        | 11351/100000 [3:21:46<14:23:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11352/100000 [3:21:47<14:24:29,  1.71it/s]
Train steps ... :  11%|█▏        | 11353/100000 [3:21:47<14:23:51,  1.71it/s]
Train steps ... :  11%|█▏        | 11354/100000 [3:21:48<14:23:30,  1.71it/s]
Train steps ... :  11%|█▏        | 11355/100000 [3:21:48<14:24:04,  1.71it/s]
Train steps ... :  11%|█▏        | 11356/100000 [3:21:49<14:23:07,  1.71it/s]
Train steps ... :  11%|█▏        | 11357/100000 [3:21:50<14:25:16,  1.71it/s]
Train steps ... :  11%|█▏        | 11358/100000 [3:21:50<14:24:31,  1.71it/s]
Train steps ... :  11%|█▏        | 11359/100000 [3:21:51<14:24:26,  1.71it/s]
Train steps ... :  11%|█▏        | 11360/100000 [3:21:51<14:23:31,  1.71it/s]
Train steps ... :  11%|█▏        | 11361/100000 [3:21:52<14:23:14,  1.71it/s]
Train steps ... :  11%|█▏        | 11362/100000 [3:21:52<14:23:05,  1.71it/s]
Train steps ... :  11%|█▏        | 11363/100000 [3:21:53<14:22:55,  1.71it/s]
Train steps ... :  11%|█▏        | 11364/100000 [3:21:54<14:23:15,  1.71it/s]
Train steps ... :  11%|█▏        | 11365/100000 [3:21:54<14:23:54,  1.71it/s]
Train steps ... :  11%|█▏        | 11366/100000 [3:21:55<14:23:34,  1.71it/s]
Train steps ... :  11%|█▏        | 11367/100000 [3:21:55<14:23:47,  1.71it/s]
Train steps ... :  11%|█▏        | 11368/100000 [3:21:56<14:23:30,  1.71it/s]
Train steps ... :  11%|█▏        | 11369/100000 [3:21:57<14:23:21,  1.71it/s]
Train steps ... :  11%|█▏        | 11370/100000 [3:21:57<14:25:03,  1.71it/s]
Train steps ... :  11%|█▏        | 11371/100000 [3:21:58<14:23:44,  1.71it/s]
Train steps ... :  11%|█▏        | 11372/100000 [3:21:58<14:23:28,  1.71it/s]
Train steps ... :  11%|█▏        | 11373/100000 [3:21:59<14:22:40,  1.71it/s]
Train steps ... :  11%|█▏        | 11374/100000 [3:21:59<14:24:17,  1.71it/s]
Train steps ... :  11%|█▏        | 11375/100000 [3:22:00<14:23:31,  1.71it/s]Step... (11375 / 100000 | Loss: 1.6270983219146729, Learning Rate: 8.907035175879398e-05)
+
                                                                             
Step... (11375 / 100000 | Loss: 0.8989154100418091, Learning Rate: 8.907035175879398e-05)
+
Train steps ... :  11%|█▏        | 11375/100000 [3:22:00<14:23:31,  1.71it/s]
Train steps ... :  11%|█▏        | 11376/100000 [3:22:01<14:24:25,  1.71it/s]
Train steps ... :  11%|█▏        | 11377/100000 [3:22:01<14:23:50,  1.71it/s]
Train steps ... :  11%|█▏        | 11378/100000 [3:22:02<14:23:11,  1.71it/s]
Train steps ... :  11%|█▏        | 11379/100000 [3:22:02<14:23:35,  1.71it/s]
Train steps ... :  11%|█▏        | 11380/100000 [3:22:03<14:23:15,  1.71it/s]
Train steps ... :  11%|█▏        | 11381/100000 [3:22:04<14:23:35,  1.71it/s]
Train steps ... :  11%|█▏        | 11382/100000 [3:22:04<14:22:53,  1.71it/s]
Train steps ... :  11%|█▏        | 11383/100000 [3:22:05<14:23:43,  1.71it/s]
Train steps ... :  11%|█▏        | 11384/100000 [3:22:05<14:22:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11385/100000 [3:22:06<14:24:20,  1.71it/s]
Train steps ... :  11%|█▏        | 11386/100000 [3:22:06<14:23:30,  1.71it/s]
Train steps ... :  11%|█▏        | 11387/100000 [3:22:07<14:24:01,  1.71it/s]
Train steps ... :  11%|█▏        | 11388/100000 [3:22:08<14:23:23,  1.71it/s]
Train steps ... :  11%|█▏        | 11389/100000 [3:22:08<14:22:41,  1.71it/s]
Train steps ... :  11%|█▏        | 11390/100000 [3:22:09<14:23:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11391/100000 [3:22:09<14:22:31,  1.71it/s]
Train steps ... :  11%|█▏        | 11392/100000 [3:22:10<14:22:34,  1.71it/s]
Train steps ... :  11%|█▏        | 11393/100000 [3:22:11<14:23:13,  1.71it/s]
Train steps ... :  11%|█▏        | 11394/100000 [3:22:11<14:24:13,  1.71it/s]
Train steps ... :  11%|█▏        | 11395/100000 [3:22:12<14:24:00,  1.71it/s]
Train steps ... :  11%|█▏        | 11396/100000 [3:22:12<14:24:51,  1.71it/s]
Train steps ... :  11%|█▏        | 11397/100000 [3:22:13<14:24:09,  1.71it/s]
Train steps ... :  11%|█▏        | 11398/100000 [3:22:14<14:23:50,  1.71it/s]
Train steps ... :  11%|█▏        | 11399/100000 [3:22:14<14:23:26,  1.71it/s]
Train steps ... :  11%|█▏        | 11400/100000 [3:22:15<14:23:01,  1.71it/s]Step... (11400 / 100000 | Loss: 1.157334566116333, Learning Rate: 8.904522613065326e-05)
+
                                                                             
Step... (11400 / 100000 | Loss: 1.36027193069458, Learning Rate: 8.904522613065326e-05)
+
Train steps ... :  11%|█▏        | 11400/100000 [3:22:15<14:23:01,  1.71it/s]
Train steps ... :  11%|█▏        | 11401/100000 [3:22:15<14:23:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11402/100000 [3:22:16<14:22:54,  1.71it/s]
Train steps ... :  11%|█▏        | 11403/100000 [3:22:16<14:22:53,  1.71it/s]
Train steps ... :  11%|█▏        | 11404/100000 [3:22:17<14:22:28,  1.71it/s]
Train steps ... :  11%|█▏        | 11405/100000 [3:22:18<14:22:41,  1.71it/s]
Train steps ... :  11%|█▏        | 11406/100000 [3:22:18<14:22:14,  1.71it/s]
Train steps ... :  11%|█▏        | 11407/100000 [3:22:19<14:22:28,  1.71it/s]
Train steps ... :  11%|█▏        | 11408/100000 [3:22:19<14:23:31,  1.71it/s]
Train steps ... :  11%|█▏        | 11409/100000 [3:22:20<14:23:13,  1.71it/s]
Train steps ... :  11%|█▏        | 11410/100000 [3:22:21<14:23:03,  1.71it/s]
Train steps ... :  11%|█▏        | 11411/100000 [3:22:21<14:22:54,  1.71it/s]
Train steps ... :  11%|█▏        | 11412/100000 [3:22:22<14:23:25,  1.71it/s]
Train steps ... :  11%|█▏        | 11413/100000 [3:22:22<14:23:17,  1.71it/s]
Train steps ... :  11%|█▏        | 11414/100000 [3:22:23<14:23:50,  1.71it/s]
Train steps ... :  11%|█▏        | 11415/100000 [3:22:23<14:23:31,  1.71it/s]
Train steps ... :  11%|█▏        | 11416/100000 [3:22:24<14:23:58,  1.71it/s]
Train steps ... :  11%|█▏        | 11417/100000 [3:22:25<14:24:14,  1.71it/s]
Train steps ... :  11%|█▏        | 11418/100000 [3:22:25<14:23:18,  1.71it/s]
Train steps ... :  11%|█▏        | 11419/100000 [3:22:26<14:24:06,  1.71it/s]
Train steps ... :  11%|█▏        | 11420/100000 [3:22:26<14:24:32,  1.71it/s]
Train steps ... :  11%|█▏        | 11421/100000 [3:22:27<14:23:36,  1.71it/s]
Train steps ... :  11%|█▏        | 11422/100000 [3:22:28<14:23:10,  1.71it/s]
Train steps ... :  11%|█▏        | 11423/100000 [3:22:28<14:23:03,  1.71it/s]
Train steps ... :  11%|█▏        | 11424/100000 [3:22:29<14:24:28,  1.71it/s]
Train steps ... :  11%|█▏        | 11425/100000 [3:22:29<14:24:18,  1.71it/s]Step... (11425 / 100000 | Loss: 1.4337732791900635, Learning Rate: 8.902010050251257e-05)
+
                                                                             
Step... (11425 / 100000 | Loss: 1.130880355834961, Learning Rate: 8.902010050251257e-05)
+
Train steps ... :  11%|█▏        | 11425/100000 [3:22:30<14:24:18,  1.71it/s]
Train steps ... :  11%|█▏        | 11426/100000 [3:22:30<14:23:54,  1.71it/s]
Train steps ... :  11%|█▏        | 11427/100000 [3:22:30<14:23:53,  1.71it/s]
Train steps ... :  11%|█▏        | 11428/100000 [3:22:31<14:23:57,  1.71it/s]
Train steps ... :  11%|█▏        | 11429/100000 [3:22:32<14:23:42,  1.71it/s]
Train steps ... :  11%|█▏        | 11430/100000 [3:22:32<14:24:03,  1.71it/s]
Train steps ... :  11%|█▏        | 11431/100000 [3:22:33<14:24:15,  1.71it/s]
Train steps ... :  11%|█▏        | 11432/100000 [3:22:33<14:23:42,  1.71it/s]
Train steps ... :  11%|█▏        | 11433/100000 [3:22:34<14:23:28,  1.71it/s]
Train steps ... :  11%|█▏        | 11434/100000 [3:22:35<14:23:03,  1.71it/s]
Train steps ... :  11%|█▏        | 11435/100000 [3:22:35<14:23:51,  1.71it/s]
Train steps ... :  11%|█▏        | 11436/100000 [3:22:36<14:22:53,  1.71it/s]
Train steps ... :  11%|█▏        | 11437/100000 [3:22:36<14:23:08,  1.71it/s]
Train steps ... :  11%|█▏        | 11438/100000 [3:22:37<14:22:38,  1.71it/s]
Train steps ... :  11%|█▏        | 11439/100000 [3:22:37<14:21:44,  1.71it/s]
Train steps ... :  11%|█▏        | 11440/100000 [3:22:38<14:21:57,  1.71it/s]
Train steps ... :  11%|█▏        | 11441/100000 [3:22:39<14:22:04,  1.71it/s]
Train steps ... :  11%|█▏        | 11442/100000 [3:22:39<14:22:03,  1.71it/s]
Train steps ... :  11%|█▏        | 11443/100000 [3:22:40<14:22:15,  1.71it/s]
Train steps ... :  11%|█▏        | 11444/100000 [3:22:40<14:22:33,  1.71it/s]
Train steps ... :  11%|█▏        | 11445/100000 [3:22:41<14:22:02,  1.71it/s]
Train steps ... :  11%|█▏        | 11446/100000 [3:22:42<14:22:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11447/100000 [3:22:42<14:22:25,  1.71it/s]
Train steps ... :  11%|█▏        | 11448/100000 [3:22:43<14:21:59,  1.71it/s]
Train steps ... :  11%|█▏        | 11449/100000 [3:22:43<14:22:27,  1.71it/s]
Train steps ... :  11%|█▏        | 11450/100000 [3:22:44<14:22:18,  1.71it/s]Step... (11450 / 100000 | Loss: 1.4772206544876099, Learning Rate: 8.899497487437186e-05)
+
                                                                             
Step... (11450 / 100000 | Loss: 1.4435750246047974, Learning Rate: 8.899497487437186e-05)
+
Train steps ... :  11%|█▏        | 11450/100000 [3:22:44<14:22:18,  1.71it/s]
Train steps ... :  11%|█▏        | 11451/100000 [3:22:45<14:23:55,  1.71it/s]
Train steps ... :  11%|█▏        | 11452/100000 [3:22:45<14:23:33,  1.71it/s]
Train steps ... :  11%|█▏        | 11453/100000 [3:22:46<14:23:30,  1.71it/s]
Train steps ... :  11%|█▏        | 11454/100000 [3:22:46<14:22:28,  1.71it/s]
Train steps ... :  11%|█▏        | 11455/100000 [3:22:47<14:22:13,  1.71it/s]
Train steps ... :  11%|█▏        | 11456/100000 [3:22:47<14:22:20,  1.71it/s]
Train steps ... :  11%|█▏        | 11457/100000 [3:22:48<14:23:31,  1.71it/s]
Train steps ... :  11%|█▏        | 11458/100000 [3:22:49<14:22:33,  1.71it/s]
Train steps ... :  11%|█▏        | 11459/100000 [3:22:49<14:22:27,  1.71it/s]
Train steps ... :  11%|█▏        | 11460/100000 [3:22:50<14:22:29,  1.71it/s]
Train steps ... :  11%|█▏        | 11461/100000 [3:22:50<14:21:49,  1.71it/s]
Train steps ... :  11%|█▏        | 11462/100000 [3:22:51<14:21:46,  1.71it/s]
Train steps ... :  11%|█▏        | 11463/100000 [3:22:52<14:22:29,  1.71it/s]
Train steps ... :  11%|█▏        | 11464/100000 [3:22:52<14:22:08,  1.71it/s]
Train steps ... :  11%|█▏        | 11465/100000 [3:22:53<14:22:05,  1.71it/s]
Train steps ... :  11%|█▏        | 11466/100000 [3:22:53<14:22:28,  1.71it/s]
Train steps ... :  11%|█▏        | 11467/100000 [3:22:54<14:22:10,  1.71it/s]
Train steps ... :  11%|█▏        | 11468/100000 [3:22:54<14:22:57,  1.71it/s]
Train steps ... :  11%|█▏        | 11469/100000 [3:22:55<14:22:15,  1.71it/s]
Train steps ... :  11%|█▏        | 11470/100000 [3:22:56<14:22:13,  1.71it/s]
Train steps ... :  11%|█▏        | 11471/100000 [3:22:56<14:21:12,  1.71it/s]
Train steps ... :  11%|█▏        | 11472/100000 [3:22:57<14:21:25,  1.71it/s]
Train steps ... :  11%|█▏        | 11473/100000 [3:22:57<14:23:12,  1.71it/s]
Train steps ... :  11%|█▏        | 11474/100000 [3:22:58<14:22:17,  1.71it/s]
Train steps ... :  11%|█▏        | 11475/100000 [3:22:59<14:22:06,  1.71it/s]Step... (11475 / 100000 | Loss: 1.2316257953643799, Learning Rate: 8.896984924623117e-05)
+
                                                                             
Step... (11475 / 100000 | Loss: 1.4131183624267578, Learning Rate: 8.896984924623117e-05)
+
Train steps ... :  11%|█▏        | 11475/100000 [3:22:59<14:22:06,  1.71it/s]
Train steps ... :  11%|█▏        | 11476/100000 [3:22:59<14:22:20,  1.71it/s]
Train steps ... :  11%|█▏        | 11477/100000 [3:23:00<14:21:50,  1.71it/s]
Train steps ... :  11%|█▏        | 11478/100000 [3:23:00<14:23:18,  1.71it/s]
Train steps ... :  11%|█▏        | 11479/100000 [3:23:01<14:22:29,  1.71it/s]
Train steps ... :  11%|█▏        | 11480/100000 [3:23:01<14:21:44,  1.71it/s]
Train steps ... :  11%|█▏        | 11481/100000 [3:23:02<14:22:14,  1.71it/s]
Train steps ... :  11%|█▏        | 11482/100000 [3:23:03<14:22:03,  1.71it/s]
Train steps ... :  11%|█▏        | 11483/100000 [3:23:03<14:22:38,  1.71it/s]
Train steps ... :  11%|█▏        | 11484/100000 [3:23:04<14:23:36,  1.71it/s]
Train steps ... :  11%|█▏        | 11485/100000 [3:23:04<14:24:06,  1.71it/s]
Train steps ... :  11%|█▏        | 11486/100000 [3:23:05<14:22:47,  1.71it/s]
Train steps ... :  11%|█▏        | 11487/100000 [3:23:06<14:22:52,  1.71it/s]
Train steps ... :  11%|█▏        | 11488/100000 [3:23:06<14:22:00,  1.71it/s]
Train steps ... :  11%|█▏        | 11489/100000 [3:23:07<14:22:18,  1.71it/s]
Train steps ... :  11%|█▏        | 11490/100000 [3:23:07<14:22:56,  1.71it/s]
Train steps ... :  11%|█▏        | 11491/100000 [3:23:08<14:23:03,  1.71it/s]
Train steps ... :  11%|█▏        | 11492/100000 [3:23:08<14:22:45,  1.71it/s]
Train steps ... :  11%|█▏        | 11493/100000 [3:23:09<14:22:23,  1.71it/s]
Train steps ... :  11%|█▏        | 11494/100000 [3:23:10<14:22:47,  1.71it/s]
Train steps ... :  11%|█▏        | 11495/100000 [3:23:10<14:23:19,  1.71it/s]
Train steps ... :  11%|█▏        | 11496/100000 [3:23:11<14:23:21,  1.71it/s]
Train steps ... :  11%|█▏        | 11497/100000 [3:23:11<14:22:28,  1.71it/s]
Train steps ... :  11%|█▏        | 11498/100000 [3:23:12<14:22:28,  1.71it/s]
Train steps ... :  11%|█▏        | 11499/100000 [3:23:13<14:22:40,  1.71it/s]
Train steps ... :  12%|█▏        | 11500/100000 [3:23:13<14:23:16,  1.71it/s]Step... (11500 / 100000 | Loss: 1.4385087490081787, Learning Rate: 8.894472361809045e-05)
+
                                                                             
Step... (11500 / 100000 | Loss: 0.9213175773620605, Learning Rate: 8.894472361809045e-05)
+
Train steps ... :  12%|█▏        | 11500/100000 [3:23:13<14:23:16,  1.71it/s]
Train steps ... :  12%|█▏        | 11501/100000 [3:23:14<14:23:47,  1.71it/s]
Train steps ... :  12%|█▏        | 11502/100000 [3:23:14<14:23:54,  1.71it/s]
Train steps ... :  12%|█▏        | 11503/100000 [3:23:15<14:22:37,  1.71it/s]
Train steps ... :  12%|█▏        | 11504/100000 [3:23:15<14:22:18,  1.71it/s]
Train steps ... :  12%|█▏        | 11505/100000 [3:23:16<14:22:09,  1.71it/s]
Train steps ... :  12%|█▏        | 11506/100000 [3:23:17<14:21:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11507/100000 [3:23:17<14:21:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11508/100000 [3:23:18<14:21:24,  1.71it/s]
Train steps ... :  12%|█▏        | 11509/100000 [3:23:18<14:21:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11510/100000 [3:23:19<14:21:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11511/100000 [3:23:20<14:21:24,  1.71it/s]
Train steps ... :  12%|█▏        | 11512/100000 [3:23:20<14:22:39,  1.71it/s]
Train steps ... :  12%|█▏        | 11513/100000 [3:23:21<14:22:10,  1.71it/s]
Train steps ... :  12%|█▏        | 11514/100000 [3:23:21<14:21:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11515/100000 [3:23:22<14:22:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11516/100000 [3:23:23<14:21:49,  1.71it/s]
Train steps ... :  12%|█▏        | 11517/100000 [3:23:23<14:21:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11518/100000 [3:23:24<14:21:30,  1.71it/s]
Train steps ... :  12%|█▏        | 11519/100000 [3:23:24<14:22:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11520/100000 [3:23:25<14:22:24,  1.71it/s]
Train steps ... :  12%|█▏        | 11521/100000 [3:23:25<14:21:53,  1.71it/s]
Train steps ... :  12%|█▏        | 11522/100000 [3:23:26<14:22:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11523/100000 [3:23:27<14:21:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11524/100000 [3:23:27<14:21:21,  1.71it/s]
Train steps ... :  12%|█▏        | 11525/100000 [3:23:28<14:21:47,  1.71it/s]Step... (11525 / 100000 | Loss: 0.9391120672225952, Learning Rate: 8.891959798994976e-05)
+
                                                                             
Step... (11525 / 100000 | Loss: 1.25558602809906, Learning Rate: 8.891959798994976e-05)
+
Train steps ... :  12%|█▏        | 11525/100000 [3:23:28<14:21:47,  1.71it/s]
Train steps ... :  12%|█▏        | 11526/100000 [3:23:28<14:22:51,  1.71it/s]
Train steps ... :  12%|█▏        | 11527/100000 [3:23:29<14:21:32,  1.71it/s]
Train steps ... :  12%|█▏        | 11528/100000 [3:23:30<14:22:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11529/100000 [3:23:30<14:23:44,  1.71it/s]
Train steps ... :  12%|█▏        | 11530/100000 [3:23:31<14:22:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11531/100000 [3:23:31<14:22:12,  1.71it/s]
Train steps ... :  12%|█▏        | 11532/100000 [3:23:32<14:22:37,  1.71it/s]
Train steps ... :  12%|█▏        | 11533/100000 [3:23:32<14:22:42,  1.71it/s]
Train steps ... :  12%|█▏        | 11534/100000 [3:23:33<14:21:52,  1.71it/s]
Train steps ... :  12%|█▏        | 11535/100000 [3:23:34<14:23:55,  1.71it/s]
Train steps ... :  12%|█▏        | 11536/100000 [3:23:34<14:22:32,  1.71it/s]
Train steps ... :  12%|█▏        | 11537/100000 [3:23:35<14:22:11,  1.71it/s]
Train steps ... :  12%|█▏        | 11538/100000 [3:23:35<14:21:54,  1.71it/s]
Train steps ... :  12%|█▏        | 11539/100000 [3:23:36<14:21:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11540/100000 [3:23:37<14:21:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11541/100000 [3:23:37<14:21:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11542/100000 [3:23:38<14:21:14,  1.71it/s]
Train steps ... :  12%|█▏        | 11543/100000 [3:23:38<14:21:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11544/100000 [3:23:39<14:22:41,  1.71it/s]
Train steps ... :  12%|█▏        | 11545/100000 [3:23:39<14:21:53,  1.71it/s]
Train steps ... :  12%|█▏        | 11546/100000 [3:23:40<14:21:32,  1.71it/s]
Train steps ... :  12%|█▏        | 11547/100000 [3:23:41<14:21:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11548/100000 [3:23:41<14:22:26,  1.71it/s]
Train steps ... :  12%|█▏        | 11549/100000 [3:23:42<14:20:49,  1.71it/s]
Train steps ... :  12%|█▏        | 11550/100000 [3:23:42<14:21:21,  1.71it/s]Step... (11550 / 100000 | Loss: 1.2296671867370605, Learning Rate: 8.889447236180904e-05)
+
                                                                             
Step... (11550 / 100000 | Loss: 1.04275381565094, Learning Rate: 8.889447236180904e-05)
+
Train steps ... :  12%|█▏        | 11550/100000 [3:23:43<14:21:21,  1.71it/s]
Train steps ... :  12%|█▏        | 11551/100000 [3:23:43<14:22:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11552/100000 [3:23:44<14:23:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11553/100000 [3:23:44<14:22:41,  1.71it/s]
Train steps ... :  12%|█▏        | 11554/100000 [3:23:45<14:22:32,  1.71it/s]
Train steps ... :  12%|█▏        | 11555/100000 [3:23:45<14:21:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11556/100000 [3:23:46<14:21:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11557/100000 [3:23:46<14:21:25,  1.71it/s]
Train steps ... :  12%|█▏        | 11558/100000 [3:23:47<14:21:27,  1.71it/s]
Train steps ... :  12%|█▏        | 11559/100000 [3:23:48<14:21:25,  1.71it/s]
Train steps ... :  12%|█▏        | 11560/100000 [3:23:48<14:21:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11561/100000 [3:23:49<14:21:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11562/100000 [3:23:49<14:21:48,  1.71it/s]
Train steps ... :  12%|█▏        | 11563/100000 [3:23:50<14:22:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11564/100000 [3:23:51<14:22:07,  1.71it/s]
Train steps ... :  12%|█▏        | 11565/100000 [3:23:51<14:21:45,  1.71it/s]
Train steps ... :  12%|█▏        | 11566/100000 [3:23:52<14:21:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11567/100000 [3:23:52<14:22:30,  1.71it/s]
Train steps ... :  12%|█▏        | 11568/100000 [3:23:53<14:22:37,  1.71it/s]
Train steps ... :  12%|█▏        | 11569/100000 [3:23:53<14:22:10,  1.71it/s]
Train steps ... :  12%|█▏        | 11570/100000 [3:23:54<14:22:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11571/100000 [3:23:55<14:23:08,  1.71it/s]
Train steps ... :  12%|█▏        | 11572/100000 [3:23:55<14:22:28,  1.71it/s]
Train steps ... :  12%|█▏        | 11573/100000 [3:23:56<14:22:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11574/100000 [3:23:56<14:22:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11575/100000 [3:23:57<14:22:14,  1.71it/s]Step... (11575 / 100000 | Loss: 1.353564977645874, Learning Rate: 8.886934673366834e-05)
+
                                                                             
Step... (11575 / 100000 | Loss: 0.9554176330566406, Learning Rate: 8.886934673366834e-05)
+
Train steps ... :  12%|█▏        | 11575/100000 [3:23:57<14:22:14,  1.71it/s]
Train steps ... :  12%|█▏        | 11576/100000 [3:23:58<14:22:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11577/100000 [3:23:58<14:22:10,  1.71it/s]
Train steps ... :  12%|█▏        | 11578/100000 [3:23:59<14:22:07,  1.71it/s]
Train steps ... :  12%|█▏        | 11579/100000 [3:23:59<14:23:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11580/100000 [3:24:00<14:20:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11581/100000 [3:24:01<14:20:44,  1.71it/s]
Train steps ... :  12%|█▏        | 11582/100000 [3:24:01<14:20:42,  1.71it/s]
Train steps ... :  12%|█▏        | 11583/100000 [3:24:02<14:21:38,  1.71it/s]
Train steps ... :  12%|█▏        | 11584/100000 [3:24:02<14:21:08,  1.71it/s]
Train steps ... :  12%|█▏        | 11585/100000 [3:24:03<14:20:52,  1.71it/s]
Train steps ... :  12%|█▏        | 11586/100000 [3:24:03<14:20:57,  1.71it/s]
Train steps ... :  12%|█▏        | 11587/100000 [3:24:04<14:21:04,  1.71it/s]
Train steps ... :  12%|█▏        | 11588/100000 [3:24:05<14:21:30,  1.71it/s]
Train steps ... :  12%|█▏        | 11589/100000 [3:24:05<14:25:00,  1.70it/s]
Train steps ... :  12%|█▏        | 11590/100000 [3:24:06<14:21:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11591/100000 [3:24:06<14:21:38,  1.71it/s]
Train steps ... :  12%|█▏        | 11592/100000 [3:24:07<14:22:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11593/100000 [3:24:08<14:21:23,  1.71it/s]
Train steps ... :  12%|█▏        | 11594/100000 [3:24:08<14:21:48,  1.71it/s]
Train steps ... :  12%|█▏        | 11595/100000 [3:24:09<14:21:49,  1.71it/s]
Train steps ... :  12%|█▏        | 11596/100000 [3:24:09<14:21:46,  1.71it/s]
Train steps ... :  12%|█▏        | 11597/100000 [3:24:10<14:23:00,  1.71it/s]
Train steps ... :  12%|█▏        | 11598/100000 [3:24:10<14:22:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11599/100000 [3:24:11<14:22:05,  1.71it/s]
Train steps ... :  12%|█▏        | 11600/100000 [3:24:12<14:22:28,  1.71it/s]Step... (11600 / 100000 | Loss: 1.4147703647613525, Learning Rate: 8.884422110552765e-05)
+
                                                                             
Step... (11600 / 100000 | Loss: 1.3862392902374268, Learning Rate: 8.884422110552765e-05)
+
Train steps ... :  12%|█▏        | 11600/100000 [3:24:12<14:22:28,  1.71it/s]
Train steps ... :  12%|█▏        | 11601/100000 [3:24:12<14:22:14,  1.71it/s]
Train steps ... :  12%|█▏        | 11602/100000 [3:24:13<14:21:47,  1.71it/s]
Train steps ... :  12%|█▏        | 11603/100000 [3:24:13<14:21:22,  1.71it/s]
Train steps ... :  12%|█▏        | 11604/100000 [3:24:14<14:21:03,  1.71it/s]
Train steps ... :  12%|█▏        | 11605/100000 [3:24:15<14:21:11,  1.71it/s]
Train steps ... :  12%|█▏        | 11606/100000 [3:24:15<14:21:25,  1.71it/s]
Train steps ... :  12%|█▏        | 11607/100000 [3:24:16<14:20:51,  1.71it/s]
Train steps ... :  12%|█▏        | 11608/100000 [3:24:16<14:20:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11609/100000 [3:24:17<14:20:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11610/100000 [3:24:17<14:20:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11611/100000 [3:24:18<14:20:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11612/100000 [3:24:19<14:20:47,  1.71it/s]
Train steps ... :  12%|█▏        | 11613/100000 [3:24:19<14:20:43,  1.71it/s]
Train steps ... :  12%|█▏        | 11614/100000 [3:24:20<14:20:55,  1.71it/s]
Train steps ... :  12%|█▏        | 11615/100000 [3:24:20<14:21:40,  1.71it/s]
Train steps ... :  12%|█▏        | 11616/100000 [3:24:21<14:20:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11617/100000 [3:24:22<14:21:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11618/100000 [3:24:22<14:20:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11619/100000 [3:24:23<14:20:51,  1.71it/s]
Train steps ... :  12%|█▏        | 11620/100000 [3:24:23<14:21:03,  1.71it/s]
Train steps ... :  12%|█▏        | 11621/100000 [3:24:24<14:20:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11622/100000 [3:24:24<14:20:40,  1.71it/s]
Train steps ... :  12%|█▏        | 11623/100000 [3:24:25<14:21:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11624/100000 [3:24:26<14:21:05,  1.71it/s]
Train steps ... :  12%|█▏        | 11625/100000 [3:24:26<14:21:19,  1.71it/s]Step... (11625 / 100000 | Loss: 1.198929786682129, Learning Rate: 8.881909547738693e-05)
+
                                                                             
Step... (11625 / 100000 | Loss: 1.2854843139648438, Learning Rate: 8.881909547738693e-05)
+
Train steps ... :  12%|█▏        | 11625/100000 [3:24:27<14:21:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11626/100000 [3:24:27<14:21:44,  1.71it/s]
Train steps ... :  12%|█▏        | 11627/100000 [3:24:27<14:20:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11628/100000 [3:24:28<14:20:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11629/100000 [3:24:29<14:20:53,  1.71it/s]
Train steps ... :  12%|█▏        | 11630/100000 [3:24:29<14:21:06,  1.71it/s]
Train steps ... :  12%|█▏        | 11631/100000 [3:24:30<14:20:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11632/100000 [3:24:30<14:21:07,  1.71it/s]
Train steps ... :  12%|█▏        | 11633/100000 [3:24:31<14:20:16,  1.71it/s]
Train steps ... :  12%|█▏        | 11634/100000 [3:24:32<14:20:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11635/100000 [3:24:32<14:20:52,  1.71it/s]
Train steps ... :  12%|█▏        | 11636/100000 [3:24:33<14:20:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11637/100000 [3:24:33<14:21:12,  1.71it/s]
Train steps ... :  12%|█▏        | 11638/100000 [3:24:34<14:21:40,  1.71it/s]
Train steps ... :  12%|█▏        | 11639/100000 [3:24:34<14:21:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11640/100000 [3:24:35<14:21:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11641/100000 [3:24:36<14:21:13,  1.71it/s]
Train steps ... :  12%|█▏        | 11642/100000 [3:24:36<14:20:27,  1.71it/s]
Train steps ... :  12%|█▏        | 11643/100000 [3:24:37<14:21:38,  1.71it/s]
Train steps ... :  12%|█▏        | 11644/100000 [3:24:37<14:21:40,  1.71it/s]
Train steps ... :  12%|█▏        | 11645/100000 [3:24:38<14:21:06,  1.71it/s]
Train steps ... :  12%|█▏        | 11646/100000 [3:24:39<14:20:38,  1.71it/s]
Train steps ... :  12%|█▏        | 11647/100000 [3:24:39<14:20:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11648/100000 [3:24:40<14:21:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11649/100000 [3:24:40<14:20:28,  1.71it/s]
Train steps ... :  12%|█▏        | 11650/100000 [3:24:41<14:20:37,  1.71it/s]Step... (11650 / 100000 | Loss: 1.2492196559906006, Learning Rate: 8.879396984924624e-05)
+
                                                                             
Step... (11650 / 100000 | Loss: 1.5086567401885986, Learning Rate: 8.879396984924624e-05)
+
Train steps ... :  12%|█▏        | 11650/100000 [3:24:41<14:20:37,  1.71it/s]
Train steps ... :  12%|█▏        | 11651/100000 [3:24:41<14:20:38,  1.71it/s]
Train steps ... :  12%|█▏        | 11652/100000 [3:24:42<14:23:00,  1.71it/s]
Train steps ... :  12%|█▏        | 11653/100000 [3:24:43<14:21:13,  1.71it/s]
Train steps ... :  12%|█▏        | 11654/100000 [3:24:43<14:20:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11655/100000 [3:24:44<14:20:24,  1.71it/s]
Train steps ... :  12%|█▏        | 11656/100000 [3:24:44<14:20:46,  1.71it/s]
Train steps ... :  12%|█▏        | 11657/100000 [3:24:45<14:20:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11658/100000 [3:24:46<14:20:57,  1.71it/s]
Train steps ... :  12%|█▏        | 11659/100000 [3:24:46<14:21:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11660/100000 [3:24:47<14:21:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11661/100000 [3:24:47<14:20:48,  1.71it/s]
Train steps ... :  12%|█▏        | 11662/100000 [3:24:48<14:21:54,  1.71it/s]
Train steps ... :  12%|█▏        | 11663/100000 [3:24:48<14:20:28,  1.71it/s]
Train steps ... :  12%|█▏        | 11664/100000 [3:24:49<14:20:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11665/100000 [3:24:50<14:20:24,  1.71it/s]
Train steps ... :  12%|█▏        | 11666/100000 [3:24:50<14:20:30,  1.71it/s]
Train steps ... :  12%|█▏        | 11667/100000 [3:24:51<14:20:08,  1.71it/s]
Train steps ... :  12%|█▏        | 11668/100000 [3:24:51<14:20:42,  1.71it/s]
Train steps ... :  12%|█▏        | 11669/100000 [3:24:52<14:20:23,  1.71it/s]
Train steps ... :  12%|█▏        | 11670/100000 [3:24:53<14:20:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11671/100000 [3:24:53<14:20:30,  1.71it/s]
Train steps ... :  12%|█▏        | 11672/100000 [3:24:54<14:20:01,  1.71it/s]
Train steps ... :  12%|█▏        | 11673/100000 [3:24:54<14:19:44,  1.71it/s]
Train steps ... :  12%|█▏        | 11674/100000 [3:24:55<14:19:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11675/100000 [3:24:55<14:20:29,  1.71it/s]Step... (11675 / 100000 | Loss: 1.49444580078125, Learning Rate: 8.876884422110553e-05)
+
                                                                             
Step... (11675 / 100000 | Loss: 1.0411083698272705, Learning Rate: 8.876884422110553e-05)
+
Train steps ... :  12%|█▏        | 11675/100000 [3:24:56<14:20:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11676/100000 [3:24:56<14:20:25,  1.71it/s]
Train steps ... :  12%|█▏        | 11677/100000 [3:24:57<14:20:10,  1.71it/s]
Train steps ... :  12%|█▏        | 11678/100000 [3:24:57<14:19:26,  1.71it/s]
Train steps ... :  12%|█▏        | 11679/100000 [3:24:58<14:20:43,  1.71it/s]
Train steps ... :  12%|█▏        | 11680/100000 [3:24:58<14:20:06,  1.71it/s]
Train steps ... :  12%|█▏        | 11681/100000 [3:24:59<14:20:06,  1.71it/s]
Train steps ... :  12%|█▏        | 11682/100000 [3:25:00<14:19:51,  1.71it/s]
Train steps ... :  12%|█▏        | 11683/100000 [3:25:00<14:19:45,  1.71it/s]
Train steps ... :  12%|█▏        | 11684/100000 [3:25:01<14:20:26,  1.71it/s]
Train steps ... :  12%|█▏        | 11685/100000 [3:25:01<14:20:28,  1.71it/s]
Train steps ... :  12%|█▏        | 11686/100000 [3:25:02<14:19:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11687/100000 [3:25:02<14:20:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11688/100000 [3:25:03<14:20:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11689/100000 [3:25:04<14:20:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11690/100000 [3:25:04<14:21:55,  1.71it/s]
Train steps ... :  12%|█▏        | 11691/100000 [3:25:05<14:21:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11692/100000 [3:25:05<14:21:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11693/100000 [3:25:06<14:20:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11694/100000 [3:25:07<14:19:53,  1.71it/s]
Train steps ... :  12%|█▏        | 11695/100000 [3:25:07<14:19:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11696/100000 [3:25:08<14:20:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11697/100000 [3:25:08<14:21:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11698/100000 [3:25:09<14:21:01,  1.71it/s]
Train steps ... :  12%|█▏        | 11699/100000 [3:25:10<14:23:03,  1.71it/s]
Train steps ... :  12%|█▏        | 11700/100000 [3:25:10<14:21:22,  1.71it/s]Step... (11700 / 100000 | Loss: 1.1560735702514648, Learning Rate: 8.874371859296484e-05)
+
                                                                             
Step... (11700 / 100000 | Loss: 1.3147913217544556, Learning Rate: 8.874371859296484e-05)
+
Train steps ... :  12%|█▏        | 11700/100000 [3:25:10<14:21:22,  1.71it/s]
Train steps ... :  12%|█▏        | 11701/100000 [3:25:11<14:21:06,  1.71it/s]
Train steps ... :  12%|█▏        | 11702/100000 [3:25:11<14:20:45,  1.71it/s]
Train steps ... :  12%|█▏        | 11703/100000 [3:25:12<14:20:38,  1.71it/s]
Train steps ... :  12%|█▏        | 11704/100000 [3:25:12<14:21:30,  1.71it/s]
Train steps ... :  12%|█▏        | 11705/100000 [3:25:13<14:20:07,  1.71it/s]
Train steps ... :  12%|█▏        | 11706/100000 [3:25:14<14:20:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11707/100000 [3:25:14<14:20:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11708/100000 [3:25:15<14:20:26,  1.71it/s]
Train steps ... :  12%|█▏        | 11709/100000 [3:25:15<14:20:42,  1.71it/s]
Train steps ... :  12%|█▏        | 11710/100000 [3:25:16<14:19:37,  1.71it/s]
Train steps ... :  12%|█▏        | 11711/100000 [3:25:17<14:20:27,  1.71it/s]
Train steps ... :  12%|█▏        | 11712/100000 [3:25:17<14:20:05,  1.71it/s]
Train steps ... :  12%|█▏        | 11713/100000 [3:25:18<14:19:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11714/100000 [3:25:18<14:19:48,  1.71it/s]
Train steps ... :  12%|█▏        | 11715/100000 [3:25:19<14:19:32,  1.71it/s]
Train steps ... :  12%|█▏        | 11716/100000 [3:25:19<14:19:41,  1.71it/s]
Train steps ... :  12%|█▏        | 11717/100000 [3:25:20<14:19:43,  1.71it/s]
Train steps ... :  12%|█▏        | 11718/100000 [3:25:21<14:19:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11719/100000 [3:25:21<14:19:37,  1.71it/s]
Train steps ... :  12%|█▏        | 11720/100000 [3:25:22<14:20:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11721/100000 [3:25:22<14:19:52,  1.71it/s]
Train steps ... :  12%|█▏        | 11722/100000 [3:25:23<14:19:46,  1.71it/s]
Train steps ... :  12%|█▏        | 11723/100000 [3:25:24<14:19:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11724/100000 [3:25:24<14:20:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11725/100000 [3:25:25<14:20:08,  1.71it/s]Step... (11725 / 100000 | Loss: 1.4405555725097656, Learning Rate: 8.871859296482412e-05)
+
                                                                             
Step... (11725 / 100000 | Loss: 0.9817445278167725, Learning Rate: 8.871859296482412e-05)
+
Train steps ... :  12%|█▏        | 11725/100000 [3:25:25<14:20:08,  1.71it/s]
Train steps ... :  12%|█▏        | 11726/100000 [3:25:25<14:20:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11727/100000 [3:25:26<14:19:23,  1.71it/s]
Train steps ... :  12%|█▏        | 11728/100000 [3:25:26<14:19:52,  1.71it/s]
Train steps ... :  12%|█▏        | 11729/100000 [3:25:27<14:20:39,  1.71it/s]
Train steps ... :  12%|█▏        | 11730/100000 [3:25:28<14:19:42,  1.71it/s]
Train steps ... :  12%|█▏        | 11731/100000 [3:25:28<14:19:55,  1.71it/s]
Train steps ... :  12%|█▏        | 11732/100000 [3:25:29<14:19:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11733/100000 [3:25:29<14:19:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11734/100000 [3:25:30<14:19:22,  1.71it/s]
Train steps ... :  12%|█▏        | 11735/100000 [3:25:31<14:19:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11736/100000 [3:25:31<14:19:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11737/100000 [3:25:32<14:19:10,  1.71it/s]
Train steps ... :  12%|█▏        | 11738/100000 [3:25:32<14:19:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11739/100000 [3:25:33<14:19:22,  1.71it/s]
Train steps ... :  12%|█▏        | 11740/100000 [3:25:33<14:19:49,  1.71it/s]
Train steps ... :  12%|█▏        | 11741/100000 [3:25:34<14:19:16,  1.71it/s]
Train steps ... :  12%|█▏        | 11742/100000 [3:25:35<14:22:00,  1.71it/s]
Train steps ... :  12%|█▏        | 11743/100000 [3:25:35<14:20:35,  1.71it/s]
Train steps ... :  12%|█▏        | 11744/100000 [3:25:36<14:20:43,  1.71it/s]
Train steps ... :  12%|█▏        | 11745/100000 [3:25:36<14:21:35,  1.71it/s]
Train steps ... :  12%|█▏        | 11746/100000 [3:25:37<14:20:35,  1.71it/s]
Train steps ... :  12%|█▏        | 11747/100000 [3:25:38<14:20:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11748/100000 [3:25:38<14:19:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11749/100000 [3:25:39<14:19:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11750/100000 [3:25:39<14:19:27,  1.71it/s]Step... (11750 / 100000 | Loss: 1.235517978668213, Learning Rate: 8.869346733668342e-05)
+
                                                                             
Step... (11750 / 100000 | Loss: 1.6220319271087646, Learning Rate: 8.869346733668342e-05)
+
Train steps ... :  12%|█▏        | 11750/100000 [3:25:40<14:19:27,  1.71it/s]
Train steps ... :  12%|█▏        | 11751/100000 [3:25:40<14:19:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11752/100000 [3:25:40<14:19:39,  1.71it/s]
Train steps ... :  12%|█▏        | 11753/100000 [3:25:41<14:20:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11754/100000 [3:25:42<14:19:51,  1.71it/s]
Train steps ... :  12%|█▏        | 11755/100000 [3:25:42<14:20:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11756/100000 [3:25:43<14:21:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11757/100000 [3:25:43<14:20:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11758/100000 [3:25:44<14:20:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11759/100000 [3:25:45<14:19:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11760/100000 [3:25:45<14:19:41,  1.71it/s]
Train steps ... :  12%|█▏        | 11761/100000 [3:25:46<14:19:26,  1.71it/s]
Train steps ... :  12%|█▏        | 11762/100000 [3:25:46<14:19:06,  1.71it/s]
Train steps ... :  12%|█▏        | 11763/100000 [3:25:47<14:18:45,  1.71it/s]
Train steps ... :  12%|█▏        | 11764/100000 [3:25:48<14:19:14,  1.71it/s]
Train steps ... :  12%|█▏        | 11765/100000 [3:25:48<14:21:42,  1.71it/s]
Train steps ... :  12%|█▏        | 11766/100000 [3:25:49<14:21:23,  1.71it/s]
Train steps ... :  12%|█▏        | 11767/100000 [3:25:49<14:20:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11768/100000 [3:25:50<14:22:07,  1.71it/s]
Train steps ... :  12%|█▏        | 11769/100000 [3:25:50<14:21:23,  1.71it/s]
Train steps ... :  12%|█▏        | 11770/100000 [3:25:51<14:22:48,  1.70it/s]
Train steps ... :  12%|█▏        | 11771/100000 [3:25:52<14:21:28,  1.71it/s]
Train steps ... :  12%|█▏        | 11772/100000 [3:25:52<14:20:21,  1.71it/s]
Train steps ... :  12%|█▏        | 11773/100000 [3:25:53<14:18:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11774/100000 [3:25:53<14:19:05,  1.71it/s]
Train steps ... :  12%|█▏        | 11775/100000 [3:25:54<14:19:44,  1.71it/s]Step... (11775 / 100000 | Loss: 1.0465333461761475, Learning Rate: 8.866834170854271e-05)
+
                                                                             
Step... (11775 / 100000 | Loss: 1.2804042100906372, Learning Rate: 8.866834170854271e-05)
+
Train steps ... :  12%|█▏        | 11775/100000 [3:25:54<14:19:44,  1.71it/s]
Train steps ... :  12%|█▏        | 11776/100000 [3:25:55<14:19:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11777/100000 [3:25:55<14:18:39,  1.71it/s]
Train steps ... :  12%|█▏        | 11778/100000 [3:25:56<14:17:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11779/100000 [3:25:56<14:19:11,  1.71it/s]
Train steps ... :  12%|█▏        | 11780/100000 [3:25:57<14:16:42,  1.72it/s]
Train steps ... :  12%|█▏        | 11781/100000 [3:25:57<14:17:38,  1.71it/s]
Train steps ... :  12%|█▏        | 11782/100000 [3:25:58<14:17:46,  1.71it/s]
Train steps ... :  12%|█▏        | 11783/100000 [3:25:59<14:16:59,  1.72it/s]
Train steps ... :  12%|█▏        | 11784/100000 [3:25:59<14:18:57,  1.71it/s]
Train steps ... :  12%|█▏        | 11785/100000 [3:26:00<14:18:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11786/100000 [3:26:00<14:18:05,  1.71it/s]
Train steps ... :  12%|█▏        | 11787/100000 [3:26:01<14:17:26,  1.71it/s]
Train steps ... :  12%|█▏        | 11788/100000 [3:26:02<14:18:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11789/100000 [3:26:02<14:17:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11790/100000 [3:26:03<14:18:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11791/100000 [3:26:03<14:17:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11792/100000 [3:26:04<14:18:47,  1.71it/s]
Train steps ... :  12%|█▏        | 11793/100000 [3:26:04<14:19:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11794/100000 [3:26:05<14:18:51,  1.71it/s]
Train steps ... :  12%|█▏        | 11795/100000 [3:26:06<14:18:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11796/100000 [3:26:06<14:19:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11797/100000 [3:26:07<14:18:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11798/100000 [3:26:07<14:18:54,  1.71it/s]
Train steps ... :  12%|█▏        | 11799/100000 [3:26:08<14:19:05,  1.71it/s]
Train steps ... :  12%|█▏        | 11800/100000 [3:26:09<14:18:02,  1.71it/s]Step... (11800 / 100000 | Loss: 1.09784734249115, Learning Rate: 8.864321608040201e-05)
+
                                                                             
Step... (11800 / 100000 | Loss: 1.183376669883728, Learning Rate: 8.864321608040201e-05)
+
Train steps ... :  12%|█▏        | 11800/100000 [3:26:09<14:18:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11801/100000 [3:26:09<14:18:35,  1.71it/s]
Train steps ... :  12%|█▏        | 11802/100000 [3:26:10<14:18:00,  1.71it/s]
Train steps ... :  12%|█▏        | 11803/100000 [3:26:10<14:17:47,  1.71it/s]
Train steps ... :  12%|█▏        | 11804/100000 [3:26:11<14:17:30,  1.71it/s]
Train steps ... :  12%|█▏        | 11805/100000 [3:26:11<14:17:28,  1.71it/s]
Train steps ... :  12%|█▏        | 11806/100000 [3:26:12<14:17:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11807/100000 [3:26:13<14:17:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11808/100000 [3:26:13<14:18:04,  1.71it/s]
Train steps ... :  12%|█▏        | 11809/100000 [3:26:14<14:18:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11810/100000 [3:26:14<14:17:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11811/100000 [3:26:15<14:17:52,  1.71it/s]
Train steps ... :  12%|█▏        | 11812/100000 [3:26:16<14:17:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11813/100000 [3:26:16<14:17:39,  1.71it/s]
Train steps ... :  12%|█▏        | 11814/100000 [3:26:17<14:17:21,  1.71it/s]
Train steps ... :  12%|█▏        | 11815/100000 [3:26:17<14:17:28,  1.71it/s]
Train steps ... :  12%|█▏        | 11816/100000 [3:26:18<14:17:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11817/100000 [3:26:18<14:18:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11818/100000 [3:26:19<14:17:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11819/100000 [3:26:20<14:17:55,  1.71it/s]
Train steps ... :  12%|█▏        | 11820/100000 [3:26:20<14:18:09,  1.71it/s]
Train steps ... :  12%|█▏        | 11821/100000 [3:26:21<14:19:00,  1.71it/s]
Train steps ... :  12%|█▏        | 11822/100000 [3:26:21<14:18:24,  1.71it/s]
Train steps ... :  12%|█▏        | 11823/100000 [3:26:22<14:18:13,  1.71it/s]
Train steps ... :  12%|█▏        | 11824/100000 [3:26:23<14:18:18,  1.71it/s]
Train steps ... :  12%|█▏        | 11825/100000 [3:26:23<14:18:46,  1.71it/s]Step... (11825 / 100000 | Loss: 1.3989689350128174, Learning Rate: 8.861809045226132e-05)
+
                                                                             
Step... (11825 / 100000 | Loss: 1.0108786821365356, Learning Rate: 8.861809045226132e-05)
+
Train steps ... :  12%|█▏        | 11825/100000 [3:26:23<14:18:46,  1.71it/s]
Train steps ... :  12%|█▏        | 11826/100000 [3:26:24<14:18:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11827/100000 [3:26:24<14:17:45,  1.71it/s]
Train steps ... :  12%|█▏        | 11828/100000 [3:26:25<14:18:10,  1.71it/s]
Train steps ... :  12%|█▏        | 11829/100000 [3:26:25<14:18:04,  1.71it/s]
Train steps ... :  12%|█▏        | 11830/100000 [3:26:26<14:18:13,  1.71it/s]
Train steps ... :  12%|█▏        | 11831/100000 [3:26:27<14:17:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11832/100000 [3:26:27<14:17:39,  1.71it/s]
Train steps ... :  12%|█▏        | 11833/100000 [3:26:28<14:17:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11834/100000 [3:26:28<14:18:21,  1.71it/s]
Train steps ... :  12%|█▏        | 11835/100000 [3:26:29<14:17:41,  1.71it/s]
Train steps ... :  12%|█▏        | 11836/100000 [3:26:30<14:17:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11837/100000 [3:26:30<14:16:57,  1.71it/s]
Train steps ... :  12%|█▏        | 11838/100000 [3:26:31<14:16:36,  1.72it/s]
Train steps ... :  12%|█▏        | 11839/100000 [3:26:31<14:17:48,  1.71it/s]
Train steps ... :  12%|█▏        | 11840/100000 [3:26:32<14:17:04,  1.71it/s]
Train steps ... :  12%|█▏        | 11841/100000 [3:26:32<14:16:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11842/100000 [3:26:33<14:17:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11843/100000 [3:26:34<14:17:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11844/100000 [3:26:34<14:17:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11845/100000 [3:26:35<14:17:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11846/100000 [3:26:35<14:17:46,  1.71it/s]
Train steps ... :  12%|█▏        | 11847/100000 [3:26:36<14:17:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11848/100000 [3:26:37<14:18:18,  1.71it/s]
Train steps ... :  12%|█▏        | 11849/100000 [3:26:37<14:18:52,  1.71it/s]
Train steps ... :  12%|█▏        | 11850/100000 [3:26:38<14:18:18,  1.71it/s]Step... (11850 / 100000 | Loss: 1.2132734060287476, Learning Rate: 8.85929648241206e-05)
+
                                                                             
Step... (11850 / 100000 | Loss: 1.3575513362884521, Learning Rate: 8.85929648241206e-05)
+
Train steps ... :  12%|█▏        | 11850/100000 [3:26:38<14:18:18,  1.71it/s]
Train steps ... :  12%|█▏        | 11851/100000 [3:26:38<14:18:47,  1.71it/s]
Train steps ... :  12%|█▏        | 11852/100000 [3:26:39<14:17:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11853/100000 [3:26:39<14:17:45,  1.71it/s]
Train steps ... :  12%|█▏        | 11854/100000 [3:26:40<14:18:24,  1.71it/s]
Train steps ... :  12%|█▏        | 11855/100000 [3:26:41<14:18:48,  1.71it/s]
Train steps ... :  12%|█▏        | 11856/100000 [3:26:41<14:18:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11857/100000 [3:26:42<14:18:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11858/100000 [3:26:42<14:18:09,  1.71it/s]
Train steps ... :  12%|█▏        | 11859/100000 [3:26:43<14:18:28,  1.71it/s]
Train steps ... :  12%|█▏        | 11860/100000 [3:26:44<14:18:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11861/100000 [3:26:44<14:18:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11862/100000 [3:26:45<14:18:32,  1.71it/s]
Train steps ... :  12%|█▏        | 11863/100000 [3:26:45<14:18:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11864/100000 [3:26:46<14:17:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11865/100000 [3:26:46<14:17:30,  1.71it/s]
Train steps ... :  12%|█▏        | 11866/100000 [3:26:47<14:18:09,  1.71it/s]
Train steps ... :  12%|█▏        | 11867/100000 [3:26:48<14:17:39,  1.71it/s]
Train steps ... :  12%|█▏        | 11868/100000 [3:26:48<14:17:27,  1.71it/s]
Train steps ... :  12%|█▏        | 11869/100000 [3:26:49<14:18:16,  1.71it/s]
Train steps ... :  12%|█▏        | 11870/100000 [3:26:49<14:19:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11871/100000 [3:26:50<14:19:03,  1.71it/s]
Train steps ... :  12%|█▏        | 11872/100000 [3:26:51<14:19:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11873/100000 [3:26:51<14:18:41,  1.71it/s]
Train steps ... :  12%|█▏        | 11874/100000 [3:26:52<14:18:04,  1.71it/s]
Train steps ... :  12%|█▏        | 11875/100000 [3:26:52<14:18:14,  1.71it/s]Step... (11875 / 100000 | Loss: 1.5615023374557495, Learning Rate: 8.856783919597991e-05)
+
                                                                             
Step... (11875 / 100000 | Loss: 1.6208457946777344, Learning Rate: 8.856783919597991e-05)
+
Train steps ... :  12%|█▏        | 11875/100000 [3:26:53<14:18:14,  1.71it/s]
Train steps ... :  12%|█▏        | 11876/100000 [3:26:53<14:17:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11877/100000 [3:26:54<14:17:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11878/100000 [3:26:54<14:16:49,  1.71it/s]
Train steps ... :  12%|█▏        | 11879/100000 [3:26:55<14:16:43,  1.71it/s]
Train steps ... :  12%|█▏        | 11880/100000 [3:26:55<14:17:46,  1.71it/s]
Train steps ... :  12%|█▏        | 11881/100000 [3:26:56<14:17:10,  1.71it/s]
Train steps ... :  12%|█▏        | 11882/100000 [3:26:56<14:17:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11883/100000 [3:26:57<14:17:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11884/100000 [3:26:58<14:17:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11885/100000 [3:26:58<14:17:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11886/100000 [3:26:59<14:17:07,  1.71it/s]
Train steps ... :  12%|█▏        | 11887/100000 [3:26:59<14:17:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11888/100000 [3:27:00<14:17:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11889/100000 [3:27:01<14:16:53,  1.71it/s]
Train steps ... :  12%|█▏        | 11890/100000 [3:27:01<14:17:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11891/100000 [3:27:02<14:19:00,  1.71it/s]
Train steps ... :  12%|█▏        | 11892/100000 [3:27:02<14:18:32,  1.71it/s]
Train steps ... :  12%|█▏        | 11893/100000 [3:27:03<14:18:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11894/100000 [3:27:03<14:18:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11895/100000 [3:27:04<14:17:48,  1.71it/s]
Train steps ... :  12%|█▏        | 11896/100000 [3:27:05<14:18:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11897/100000 [3:27:05<14:17:45,  1.71it/s]
Train steps ... :  12%|█▏        | 11898/100000 [3:27:06<14:17:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11899/100000 [3:27:06<14:17:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11900/100000 [3:27:07<14:17:50,  1.71it/s]Step... (11900 / 100000 | Loss: 1.2413358688354492, Learning Rate: 8.85427135678392e-05)
+
                                                                             
Step... (11900 / 100000 | Loss: 1.1719238758087158, Learning Rate: 8.85427135678392e-05)
+
Train steps ... :  12%|█▏        | 11900/100000 [3:27:07<14:17:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11901/100000 [3:27:08<14:17:48,  1.71it/s]
Train steps ... :  12%|█▏        | 11902/100000 [3:27:08<14:17:11,  1.71it/s]
Train steps ... :  12%|█▏        | 11903/100000 [3:27:09<14:17:06,  1.71it/s]
Train steps ... :  12%|█▏        | 11904/100000 [3:27:09<14:17:24,  1.71it/s]
Train steps ... :  12%|█▏        | 11905/100000 [3:27:10<14:19:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11906/100000 [3:27:10<14:18:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11907/100000 [3:27:11<14:18:21,  1.71it/s]
Train steps ... :  12%|█▏        | 11908/100000 [3:27:12<14:17:06,  1.71it/s]
Train steps ... :  12%|█▏        | 11909/100000 [3:27:12<14:17:13,  1.71it/s]
Train steps ... :  12%|█▏        | 11910/100000 [3:27:13<14:17:40,  1.71it/s]
Train steps ... :  12%|█▏        | 11911/100000 [3:27:13<14:17:18,  1.71it/s]
Train steps ... :  12%|█▏        | 11912/100000 [3:27:14<14:16:51,  1.71it/s]
Train steps ... :  12%|█▏        | 11913/100000 [3:27:15<14:17:14,  1.71it/s]
Train steps ... :  12%|█▏        | 11914/100000 [3:27:15<14:17:08,  1.71it/s]
Train steps ... :  12%|█▏        | 11915/100000 [3:27:16<14:17:46,  1.71it/s]
Train steps ... :  12%|█▏        | 11916/100000 [3:27:16<14:16:41,  1.71it/s]
Train steps ... :  12%|█▏        | 11917/100000 [3:27:17<14:16:38,  1.71it/s]
Train steps ... :  12%|█▏        | 11918/100000 [3:27:17<14:17:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11919/100000 [3:27:18<14:17:11,  1.71it/s]
Train steps ... :  12%|█▏        | 11920/100000 [3:27:19<14:17:32,  1.71it/s]
Train steps ... :  12%|█▏        | 11921/100000 [3:27:19<14:17:54,  1.71it/s]
Train steps ... :  12%|█▏        | 11922/100000 [3:27:20<14:19:04,  1.71it/s]
Train steps ... :  12%|█▏        | 11923/100000 [3:27:20<14:19:58,  1.71it/s]
Train steps ... :  12%|█▏        | 11924/100000 [3:27:21<14:19:01,  1.71it/s]
Train steps ... :  12%|█▏        | 11925/100000 [3:27:22<14:21:17,  1.70it/s]Step... (11925 / 100000 | Loss: 1.2483820915222168, Learning Rate: 8.851758793969849e-05)
+
                                                                             
Step... (11925 / 100000 | Loss: 1.2022876739501953, Learning Rate: 8.851758793969849e-05)
+
Train steps ... :  12%|█▏        | 11925/100000 [3:27:22<14:21:17,  1.70it/s]
Train steps ... :  12%|█▏        | 11926/100000 [3:27:22<14:20:17,  1.71it/s]
Train steps ... :  12%|█▏        | 11927/100000 [3:27:23<14:18:57,  1.71it/s]
Train steps ... :  12%|█▏        | 11928/100000 [3:27:23<14:18:45,  1.71it/s]
Train steps ... :  12%|█▏        | 11929/100000 [3:27:24<14:18:06,  1.71it/s]
Train steps ... :  12%|█▏        | 11930/100000 [3:27:24<14:18:21,  1.71it/s]
Train steps ... :  12%|█▏        | 11931/100000 [3:27:25<14:19:00,  1.71it/s]
Train steps ... :  12%|█▏        | 11932/100000 [3:27:26<14:19:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11933/100000 [3:27:26<14:17:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11934/100000 [3:27:27<14:19:12,  1.71it/s]
Train steps ... :  12%|█▏        | 11935/100000 [3:27:27<14:18:47,  1.71it/s]
Train steps ... :  12%|█▏        | 11936/100000 [3:27:28<14:17:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11937/100000 [3:27:29<14:17:32,  1.71it/s]
Train steps ... :  12%|█▏        | 11938/100000 [3:27:29<14:17:14,  1.71it/s]
Train steps ... :  12%|█▏        | 11939/100000 [3:27:30<14:18:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11940/100000 [3:27:30<14:17:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11941/100000 [3:27:31<14:17:13,  1.71it/s]
Train steps ... :  12%|█▏        | 11942/100000 [3:27:31<14:18:35,  1.71it/s]
Train steps ... :  12%|█▏        | 11943/100000 [3:27:32<14:17:22,  1.71it/s]
Train steps ... :  12%|█▏        | 11944/100000 [3:27:33<14:17:07,  1.71it/s]
Train steps ... :  12%|█▏        | 11945/100000 [3:27:33<14:17:07,  1.71it/s]
Train steps ... :  12%|█▏        | 11946/100000 [3:27:34<14:16:04,  1.71it/s]
Train steps ... :  12%|█▏        | 11947/100000 [3:27:34<14:15:42,  1.72it/s]
Train steps ... :  12%|█▏        | 11948/100000 [3:27:35<14:15:39,  1.72it/s]
Train steps ... :  12%|█▏        | 11949/100000 [3:27:36<14:16:16,  1.71it/s]
Train steps ... :  12%|█▏        | 11950/100000 [3:27:36<14:15:57,  1.71it/s]Step... (11950 / 100000 | Loss: 1.086653232574463, Learning Rate: 8.849246231155779e-05)
+
                                                                             
Step... (11950 / 100000 | Loss: 0.8598572015762329, Learning Rate: 8.849246231155779e-05)
+
Train steps ... :  12%|█▏        | 11950/100000 [3:27:36<14:15:57,  1.71it/s]
Train steps ... :  12%|█▏        | 11951/100000 [3:27:37<14:16:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11952/100000 [3:27:37<14:17:31,  1.71it/s]
Train steps ... :  12%|█▏        | 11953/100000 [3:27:38<14:16:46,  1.71it/s]
Train steps ... :  12%|█▏        | 11954/100000 [3:27:38<14:17:56,  1.71it/s]
Train steps ... :  12%|█▏        | 11955/100000 [3:27:39<14:16:54,  1.71it/s]
Train steps ... :  12%|█▏        | 11956/100000 [3:27:40<14:16:21,  1.71it/s]
Train steps ... :  12%|█▏        | 11957/100000 [3:27:40<14:17:07,  1.71it/s]
Train steps ... :  12%|█▏        | 11958/100000 [3:27:41<14:16:47,  1.71it/s]
Train steps ... :  12%|█▏        | 11959/100000 [3:27:41<14:16:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11960/100000 [3:27:42<14:18:24,  1.71it/s]
Train steps ... :  12%|█▏        | 11961/100000 [3:27:43<14:17:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11962/100000 [3:27:43<14:17:06,  1.71it/s]
Train steps ... :  12%|█▏        | 11963/100000 [3:27:44<14:16:40,  1.71it/s]
Train steps ... :  12%|█▏        | 11964/100000 [3:27:44<14:17:22,  1.71it/s]
Train steps ... :  12%|█▏        | 11965/100000 [3:27:45<14:17:10,  1.71it/s]
Train steps ... :  12%|█▏        | 11966/100000 [3:27:46<14:18:09,  1.71it/s]
Train steps ... :  12%|█▏        | 11967/100000 [3:27:46<14:17:54,  1.71it/s]
Train steps ... :  12%|█▏        | 11968/100000 [3:27:47<14:17:20,  1.71it/s]
Train steps ... :  12%|█▏        | 11969/100000 [3:27:47<14:17:19,  1.71it/s]
Train steps ... :  12%|█▏        | 11970/100000 [3:27:48<14:17:15,  1.71it/s]
Train steps ... :  12%|█▏        | 11971/100000 [3:27:48<14:17:14,  1.71it/s]
Train steps ... :  12%|█▏        | 11972/100000 [3:27:49<14:16:50,  1.71it/s]
Train steps ... :  12%|█▏        | 11973/100000 [3:27:50<14:17:16,  1.71it/s]
Train steps ... :  12%|█▏        | 11974/100000 [3:27:50<14:16:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11975/100000 [3:27:51<14:16:42,  1.71it/s]Step... (11975 / 100000 | Loss: 1.2261934280395508, Learning Rate: 8.846733668341709e-05)
+
                                                                             
Step... (11975 / 100000 | Loss: 1.1735317707061768, Learning Rate: 8.846733668341709e-05)
+
Train steps ... :  12%|█▏        | 11975/100000 [3:27:51<14:16:42,  1.71it/s]
Train steps ... :  12%|█▏        | 11976/100000 [3:27:51<14:16:49,  1.71it/s]
Train steps ... :  12%|█▏        | 11977/100000 [3:27:52<14:16:24,  1.71it/s]
Train steps ... :  12%|█▏        | 11978/100000 [3:27:53<14:16:28,  1.71it/s]
Train steps ... :  12%|█▏        | 11979/100000 [3:27:53<14:16:27,  1.71it/s]
Train steps ... :  12%|█▏        | 11980/100000 [3:27:54<14:17:02,  1.71it/s]
Train steps ... :  12%|█▏        | 11981/100000 [3:27:54<14:18:27,  1.71it/s]
Train steps ... :  12%|█▏        | 11982/100000 [3:27:55<14:17:53,  1.71it/s]
Train steps ... :  12%|█▏        | 11983/100000 [3:27:55<14:18:36,  1.71it/s]
Train steps ... :  12%|█▏        | 11984/100000 [3:27:56<14:17:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11985/100000 [3:27:57<14:17:35,  1.71it/s]
Train steps ... :  12%|█▏        | 11986/100000 [3:27:57<14:17:23,  1.71it/s]
Train steps ... :  12%|█▏        | 11987/100000 [3:27:58<14:17:50,  1.71it/s]
Train steps ... :  12%|█��        | 11988/100000 [3:27:58<14:17:13,  1.71it/s]
Train steps ... :  12%|█▏        | 11989/100000 [3:27:59<14:16:32,  1.71it/s]
Train steps ... :  12%|█▏        | 11990/100000 [3:28:00<14:16:30,  1.71it/s]
Train steps ... :  12%|█▏        | 11991/100000 [3:28:00<14:16:43,  1.71it/s]
Train steps ... :  12%|█▏        | 11992/100000 [3:28:01<14:16:33,  1.71it/s]
Train steps ... :  12%|█▏        | 11993/100000 [3:28:01<14:17:29,  1.71it/s]
Train steps ... :  12%|█▏        | 11994/100000 [3:28:02<14:16:59,  1.71it/s]
Train steps ... :  12%|█▏        | 11995/100000 [3:28:02<14:16:53,  1.71it/s]
Train steps ... :  12%|█▏        | 11996/100000 [3:28:03<14:16:34,  1.71it/s]
Train steps ... :  12%|█▏        | 11997/100000 [3:28:04<14:16:16,  1.71it/s]
Train steps ... :  12%|█▏        | 11998/100000 [3:28:04<14:15:55,  1.71it/s]
Train steps ... :  12%|█▏        | 11999/100000 [3:28:05<14:17:55,  1.71it/s]
Train steps ... :  12%|█▏        | 12000/100000 [3:28:05<14:16:57,  1.71it/s]Step... (12000 / 100000 | Loss: 1.2695753574371338, Learning Rate: 8.84422110552764e-05)
+
                                                                             
Step... (12000 / 100000 | Loss: 1.313429355621338, Learning Rate: 8.84422110552764e-05)
+
Train steps ... :  12%|█▏        | 12000/100000 [3:28:06<14:16:57,  1.71it/s]
Train steps ... :  12%|█▏        | 12001/100000 [3:28:06<14:17:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12002/100000 [3:28:07<14:16:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12003/100000 [3:28:07<14:17:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12004/100000 [3:28:08<14:17:30,  1.71it/s]
Train steps ... :  12%|█▏        | 12005/100000 [3:28:08<14:16:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12006/100000 [3:28:09<14:16:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12007/100000 [3:28:09<14:16:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12008/100000 [3:28:10<14:16:00,  1.71it/s]
Train steps ... :  12%|█▏        | 12009/100000 [3:28:11<14:16:30,  1.71it/s]
Train steps ... :  12%|█▏        | 12010/100000 [3:28:11<14:16:06,  1.71it/s]
Train steps ... :  12%|█▏        | 12011/100000 [3:28:12<14:16:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12012/100000 [3:28:12<14:17:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12013/100000 [3:28:13<14:16:47,  1.71it/s]
Train steps ... :  12%|█▏        | 12014/100000 [3:28:14<14:16:36,  1.71it/s]
Train steps ... :  12%|█▏        | 12015/100000 [3:28:14<14:17:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12016/100000 [3:28:15<14:17:44,  1.71it/s]
Train steps ... :  12%|█▏        | 12017/100000 [3:28:15<14:17:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12018/100000 [3:28:16<14:20:15,  1.70it/s]
Train steps ... :  12%|█▏        | 12019/100000 [3:28:16<14:16:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12020/100000 [3:28:17<14:16:41,  1.71it/s]
Train steps ... :  12%|█▏        | 12021/100000 [3:28:18<14:17:27,  1.71it/s]
Train steps ... :  12%|█▏        | 12022/100000 [3:28:18<14:16:45,  1.71it/s]
Train steps ... :  12%|█▏        | 12023/100000 [3:28:19<14:16:48,  1.71it/s]
Train steps ... :  12%|█▏        | 12024/100000 [3:28:19<14:16:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12025/100000 [3:28:20<14:16:03,  1.71it/s]Step... (12025 / 100000 | Loss: 1.3176195621490479, Learning Rate: 8.841708542713568e-05)
+
                                                                             
Step... (12025 / 100000 | Loss: 0.944903552532196, Learning Rate: 8.841708542713568e-05)
+
Train steps ... :  12%|█▏        | 12025/100000 [3:28:20<14:16:03,  1.71it/s]
Train steps ... :  12%|█▏        | 12026/100000 [3:28:21<14:16:45,  1.71it/s]
Train steps ... :  12%|█▏        | 12027/100000 [3:28:21<14:16:24,  1.71it/s]
Train steps ... :  12%|█▏        | 12028/100000 [3:28:22<14:16:45,  1.71it/s]
Train steps ... :  12%|█▏        | 12029/100000 [3:28:22<14:15:54,  1.71it/s]
Train steps ... :  12%|█▏        | 12030/100000 [3:28:23<14:16:24,  1.71it/s]
Train steps ... :  12%|█▏        | 12031/100000 [3:28:23<14:16:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12032/100000 [3:28:24<14:16:36,  1.71it/s]
Train steps ... :  12%|█▏        | 12033/100000 [3:28:25<14:16:54,  1.71it/s]
Train steps ... :  12%|█▏        | 12034/100000 [3:28:25<14:17:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12035/100000 [3:28:26<14:16:39,  1.71it/s]
Train steps ... :  12%|█▏        | 12036/100000 [3:28:26<14:16:18,  1.71it/s]
Train steps ... :  12%|█▏        | 12037/100000 [3:28:27<14:16:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12038/100000 [3:28:28<14:16:35,  1.71it/s]
Train steps ... :  12%|█▏        | 12039/100000 [3:28:28<14:16:36,  1.71it/s]
Train steps ... :  12%|█▏        | 12040/100000 [3:28:29<14:17:24,  1.71it/s]
Train steps ... :  12%|█▏        | 12041/100000 [3:28:29<14:16:37,  1.71it/s]
Train steps ... :  12%|█▏        | 12042/100000 [3:28:30<14:17:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12043/100000 [3:28:31<14:18:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12044/100000 [3:28:31<14:17:10,  1.71it/s]
Train steps ... :  12%|█▏        | 12045/100000 [3:28:32<14:16:55,  1.71it/s]
Train steps ... :  12%|█▏        | 12046/100000 [3:28:32<14:17:08,  1.71it/s]
Train steps ... :  12%|█▏        | 12047/100000 [3:28:33<14:16:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12048/100000 [3:28:33<14:16:29,  1.71it/s]
Train steps ... :  12%|█▏        | 12049/100000 [3:28:34<14:16:39,  1.71it/s]
Train steps ... :  12%|█▏        | 12050/100000 [3:28:35<14:17:34,  1.71it/s]Step... (12050 / 100000 | Loss: 1.3020514249801636, Learning Rate: 8.839195979899499e-05)
+
                                                                             
Step... (12050 / 100000 | Loss: 1.217513084411621, Learning Rate: 8.839195979899499e-05)
+
Train steps ... :  12%|█▏        | 12050/100000 [3:28:35<14:17:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12051/100000 [3:28:35<14:18:45,  1.71it/s]
Train steps ... :  12%|█▏        | 12052/100000 [3:28:36<14:17:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12053/100000 [3:28:36<14:17:53,  1.71it/s]
Train steps ... :  12%|█▏        | 12054/100000 [3:28:37<14:17:28,  1.71it/s]
Train steps ... :  12%|█▏        | 12055/100000 [3:28:38<14:16:15,  1.71it/s]
Train steps ... :  12%|█▏        | 12056/100000 [3:28:38<14:18:48,  1.71it/s]
Train steps ... :  12%|█▏        | 12057/100000 [3:28:39<14:17:10,  1.71it/s]
Train steps ... :  12%|█▏        | 12058/100000 [3:28:39<14:16:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12059/100000 [3:28:40<14:16:05,  1.71it/s]
Train steps ... :  12%|█▏        | 12060/100000 [3:28:40<14:16:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12061/100000 [3:28:41<14:16:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12062/100000 [3:28:42<14:16:00,  1.71it/s]
Train steps ... :  12%|█▏        | 12063/100000 [3:28:42<14:16:32,  1.71it/s]
Train steps ... :  12%|█▏        | 12064/100000 [3:28:43<14:16:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12065/100000 [3:28:43<14:17:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12066/100000 [3:28:44<14:16:39,  1.71it/s]
Train steps ... :  12%|█▏        | 12067/100000 [3:28:45<14:18:41,  1.71it/s]
Train steps ... :  12%|█▏        | 12068/100000 [3:28:45<14:17:05,  1.71it/s]
Train steps ... :  12%|█▏        | 12069/100000 [3:28:46<14:16:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12070/100000 [3:28:46<14:15:57,  1.71it/s]
Train steps ... :  12%|█▏        | 12071/100000 [3:28:47<14:16:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12072/100000 [3:28:47<14:15:39,  1.71it/s]
Train steps ... :  12%|█▏        | 12073/100000 [3:28:48<14:16:23,  1.71it/s]
Train steps ... :  12%|█▏        | 12074/100000 [3:28:49<14:15:59,  1.71it/s]
Train steps ... :  12%|█▏        | 12075/100000 [3:28:49<14:16:59,  1.71it/s]Step... (12075 / 100000 | Loss: 1.1925957202911377, Learning Rate: 8.836683417085427e-05)
+
                                                                             
Step... (12075 / 100000 | Loss: 1.2621548175811768, Learning Rate: 8.836683417085427e-05)
+
Train steps ... :  12%|█▏        | 12075/100000 [3:28:50<14:16:59,  1.71it/s]
Train steps ... :  12%|█▏        | 12076/100000 [3:28:50<14:16:38,  1.71it/s]
Train steps ... :  12%|█▏        | 12077/100000 [3:28:50<14:15:42,  1.71it/s]
Train steps ... :  12%|█▏        | 12078/100000 [3:28:51<14:16:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12079/100000 [3:28:52<14:16:19,  1.71it/s]
Train steps ... :  12%|█▏        | 12080/100000 [3:28:52<14:16:21,  1.71it/s]
Train steps ... :  12%|█▏        | 12081/100000 [3:28:53<14:15:28,  1.71it/s]
Train steps ... :  12%|█▏        | 12082/100000 [3:28:53<14:16:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12083/100000 [3:28:54<14:15:54,  1.71it/s]
Train steps ... :  12%|█▏        | 12084/100000 [3:28:54<14:15:22,  1.71it/s]
Train steps ... :  12%|█▏        | 12085/100000 [3:28:55<14:16:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12086/100000 [3:28:56<14:17:19,  1.71it/s]
Train steps ... :  12%|█▏        | 12087/100000 [3:28:56<14:16:50,  1.71it/s]
Train steps ... :  12%|█▏        | 12088/100000 [3:28:57<14:18:04,  1.71it/s]
Train steps ... :  12%|█▏        | 12089/100000 [3:28:57<14:17:55,  1.71it/s]
Train steps ... :  12%|█▏        | 12090/100000 [3:28:58<14:17:04,  1.71it/s]
Train steps ... :  12%|█▏        | 12091/100000 [3:28:59<14:16:28,  1.71it/s]
Train steps ... :  12%|█▏        | 12092/100000 [3:28:59<14:15:33,  1.71it/s]
Train steps ... :  12%|█▏        | 12093/100000 [3:29:00<14:15:30,  1.71it/s]
Train steps ... :  12%|█▏        | 12094/100000 [3:29:00<14:15:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12095/100000 [3:29:01<14:14:53,  1.71it/s]
Train steps ... :  12%|█▏        | 12096/100000 [3:29:01<14:15:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12097/100000 [3:29:02<14:15:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12098/100000 [3:29:03<14:17:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12099/100000 [3:29:03<14:16:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12100/100000 [3:29:04<14:16:38,  1.71it/s]Step... (12100 / 100000 | Loss: 1.5682008266448975, Learning Rate: 8.834170854271357e-05)
+
                                                                             
Step... (12100 / 100000 | Loss: 1.1092865467071533, Learning Rate: 8.834170854271357e-05)
+
Train steps ... :  12%|█▏        | 12100/100000 [3:29:04<14:16:38,  1.71it/s]
Train steps ... :  12%|█▏        | 12101/100000 [3:29:04<14:17:32,  1.71it/s]
Train steps ... :  12%|█▏        | 12102/100000 [3:29:05<14:16:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12103/100000 [3:29:06<14:16:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12104/100000 [3:29:06<14:15:51,  1.71it/s]
Train steps ... :  12%|█▏        | 12105/100000 [3:29:07<14:16:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12106/100000 [3:29:07<14:15:43,  1.71it/s]
Train steps ... :  12%|█▏        | 12107/100000 [3:29:08<14:16:19,  1.71it/s]
Train steps ... :  12%|█▏        | 12108/100000 [3:29:08<14:16:00,  1.71it/s]
Train steps ... :  12%|█▏        | 12109/100000 [3:29:09<14:15:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12110/100000 [3:29:10<14:16:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12111/100000 [3:29:10<14:15:57,  1.71it/s]
Train steps ... :  12%|█▏        | 12112/100000 [3:29:11<14:16:29,  1.71it/s]
Train steps ... :  12%|█▏        | 12113/100000 [3:29:11<14:17:26,  1.71it/s]
Train steps ... :  12%|█▏        | 12114/100000 [3:29:12<14:16:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12115/100000 [3:29:13<14:16:11,  1.71it/s]
Train steps ... :  12%|█▏        | 12116/100000 [3:29:13<14:15:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12117/100000 [3:29:14<14:15:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12118/100000 [3:29:14<14:16:43,  1.71it/s]
Train steps ... :  12%|█▏        | 12119/100000 [3:29:15<14:16:15,  1.71it/s]
Train steps ... :  12%|█▏        | 12120/100000 [3:29:16<14:18:35,  1.71it/s]
Train steps ... :  12%|█▏        | 12121/100000 [3:29:16<14:18:41,  1.71it/s]
Train steps ... :  12%|█▏        | 12122/100000 [3:29:17<14:17:47,  1.71it/s]
Train steps ... :  12%|█▏        | 12123/100000 [3:29:17<14:17:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12124/100000 [3:29:18<14:16:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12125/100000 [3:29:18<14:16:54,  1.71it/s]Step... (12125 / 100000 | Loss: 1.1304548978805542, Learning Rate: 8.831658291457287e-05)
+
                                                                             
Step... (12125 / 100000 | Loss: 1.090938687324524, Learning Rate: 8.831658291457287e-05)
+
Train steps ... :  12%|█▏        | 12125/100000 [3:29:19<14:16:54,  1.71it/s]
Train steps ... :  12%|█▏        | 12126/100000 [3:29:19<14:16:48,  1.71it/s]
Train steps ... :  12%|█▏        | 12127/100000 [3:29:20<14:16:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12128/100000 [3:29:20<14:15:42,  1.71it/s]
Train steps ... :  12%|█▏        | 12129/100000 [3:29:21<14:16:21,  1.71it/s]
Train steps ... :  12%|█▏        | 12130/100000 [3:29:21<14:15:08,  1.71it/s]
Train steps ... :  12%|█▏        | 12131/100000 [3:29:22<14:15:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12132/100000 [3:29:23<14:15:36,  1.71it/s]
Train steps ... :  12%|█▏        | 12133/100000 [3:29:23<14:15:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12134/100000 [3:29:24<14:16:37,  1.71it/s]
Train steps ... :  12%|█▏        | 12135/100000 [3:29:24<14:15:32,  1.71it/s]
Train steps ... :  12%|█▏        | 12136/100000 [3:29:25<14:15:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12137/100000 [3:29:25<14:15:05,  1.71it/s]
Train steps ... :  12%|█▏        | 12138/100000 [3:29:26<14:15:37,  1.71it/s]
Train steps ... :  12%|█▏        | 12139/100000 [3:29:27<14:15:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12140/100000 [3:29:27<14:15:23,  1.71it/s]
Train steps ... :  12%|█▏        | 12141/100000 [3:29:28<14:15:44,  1.71it/s]
Train steps ... :  12%|█▏        | 12142/100000 [3:29:28<14:15:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12143/100000 [3:29:29<14:15:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12144/100000 [3:29:30<14:15:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12145/100000 [3:29:30<14:15:38,  1.71it/s]
Train steps ... :  12%|█▏        | 12146/100000 [3:29:31<14:16:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12147/100000 [3:29:31<14:16:58,  1.71it/s]
Train steps ... :  12%|█▏        | 12148/100000 [3:29:32<14:16:57,  1.71it/s]
Train steps ... :  12%|█▏        | 12149/100000 [3:29:32<14:16:08,  1.71it/s]
Train steps ... :  12%|█▏        | 12150/100000 [3:29:33<14:15:30,  1.71it/s]Step... (12150 / 100000 | Loss: 1.2029509544372559, Learning Rate: 8.829145728643216e-05)
+
                                                                             
Step... (12150 / 100000 | Loss: 1.2384178638458252, Learning Rate: 8.829145728643216e-05)
+
Train steps ... :  12%|█▏        | 12150/100000 [3:29:33<14:15:30,  1.71it/s]
Train steps ... :  12%|█▏        | 12151/100000 [3:29:34<14:15:24,  1.71it/s]
Train steps ... :  12%|█▏        | 12152/100000 [3:29:34<14:15:32,  1.71it/s]
Train steps ... :  12%|█▏        | 12153/100000 [3:29:35<14:16:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12154/100000 [3:29:35<14:14:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12155/100000 [3:29:36<14:17:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12156/100000 [3:29:37<14:15:30,  1.71it/s]
Train steps ... :  12%|█▏        | 12157/100000 [3:29:37<14:15:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12158/100000 [3:29:38<14:14:37,  1.71it/s]
Train steps ... :  12%|█▏        | 12159/100000 [3:29:38<14:14:50,  1.71it/s]
Train steps ... :  12%|█▏        | 12160/100000 [3:29:39<14:14:55,  1.71it/s]
Train steps ... :  12%|█▏        | 12161/100000 [3:29:39<14:14:24,  1.71it/s]
Train steps ... :  12%|█▏        | 12162/100000 [3:29:40<14:14:44,  1.71it/s]
Train steps ... :  12%|█▏        | 12163/100000 [3:29:41<14:14:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12164/100000 [3:29:41<14:15:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12165/100000 [3:29:42<14:14:48,  1.71it/s]
Train steps ... :  12%|█▏        | 12166/100000 [3:29:42<14:15:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12167/100000 [3:29:43<14:15:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12168/100000 [3:29:44<14:15:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12169/100000 [3:29:44<14:14:54,  1.71it/s]
Train steps ... :  12%|█▏        | 12170/100000 [3:29:45<14:14:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12171/100000 [3:29:45<14:14:29,  1.71it/s]
Train steps ... :  12%|█▏        | 12172/100000 [3:29:46<14:15:28,  1.71it/s]
Train steps ... :  12%|█▏        | 12173/100000 [3:29:46<14:14:57,  1.71it/s]
Train steps ... :  12%|█▏        | 12174/100000 [3:29:47<14:14:36,  1.71it/s]
Train steps ... :  12%|█▏        | 12175/100000 [3:29:48<14:14:55,  1.71it/s]Step... (12175 / 100000 | Loss: 1.0383837223052979, Learning Rate: 8.826633165829146e-05)
+
                                                                             
Step... (12175 / 100000 | Loss: 1.2711951732635498, Learning Rate: 8.826633165829146e-05)
+
Train steps ... :  12%|█▏        | 12175/100000 [3:29:48<14:14:55,  1.71it/s]
Train steps ... :  12%|█▏        | 12176/100000 [3:29:48<14:16:23,  1.71it/s]
Train steps ... :  12%|█▏        | 12177/100000 [3:29:49<14:15:57,  1.71it/s]
Train steps ... :  12%|█▏        | 12178/100000 [3:29:49<14:17:23,  1.71it/s]
Train steps ... :  12%|█▏        | 12179/100000 [3:29:50<14:16:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12180/100000 [3:29:51<14:14:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12181/100000 [3:29:51<14:14:24,  1.71it/s]
Train steps ... :  12%|█▏        | 12182/100000 [3:29:52<14:14:45,  1.71it/s]
Train steps ... :  12%|█▏        | 12183/100000 [3:29:52<14:14:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12184/100000 [3:29:53<14:14:19,  1.71it/s]
Train steps ... :  12%|█▏        | 12185/100000 [3:29:53<14:14:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12186/100000 [3:29:54<14:17:53,  1.71it/s]
Train steps ... :  12%|█▏        | 12187/100000 [3:29:55<14:17:10,  1.71it/s]
Train steps ... :  12%|█▏        | 12188/100000 [3:29:55<14:16:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12189/100000 [3:29:56<14:15:44,  1.71it/s]
Train steps ... :  12%|█▏        | 12190/100000 [3:29:56<14:16:35,  1.71it/s]
Train steps ... :  12%|█▏        | 12191/100000 [3:29:57<14:15:38,  1.71it/s]
Train steps ... :  12%|█▏        | 12192/100000 [3:29:58<14:15:55,  1.71it/s]
Train steps ... :  12%|█▏        | 12193/100000 [3:29:58<14:15:12,  1.71it/s]
Train steps ... :  12%|█▏        | 12194/100000 [3:29:59<14:15:27,  1.71it/s]
Train steps ... :  12%|█▏        | 12195/100000 [3:29:59<14:16:04,  1.71it/s]
Train steps ... :  12%|█▏        | 12196/100000 [3:30:00<14:15:31,  1.71it/s]
Train steps ... :  12%|█▏        | 12197/100000 [3:30:01<14:15:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12198/100000 [3:30:01<14:14:45,  1.71it/s]
Train steps ... :  12%|█▏        | 12199/100000 [3:30:02<14:15:00,  1.71it/s]
Train steps ... :  12%|█▏        | 12200/100000 [3:30:02<14:15:46,  1.71it/s]Step... (12200 / 100000 | Loss: 0.9467694759368896, Learning Rate: 8.824120603015076e-05)
+
                                                                             
Step... (12200 / 100000 | Loss: 1.1621490716934204, Learning Rate: 8.824120603015076e-05)
+
Train steps ... :  12%|█▏        | 12200/100000 [3:30:03<14:15:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12201/100000 [3:30:03<14:16:40,  1.71it/s]
Train steps ... :  12%|█▏        | 12202/100000 [3:30:03<14:15:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12203/100000 [3:30:04<14:14:57,  1.71it/s]
Train steps ... :  12%|█▏        | 12204/100000 [3:30:05<14:15:47,  1.71it/s]
Train steps ... :  12%|█▏        | 12205/100000 [3:30:05<14:14:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12206/100000 [3:30:06<14:14:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12207/100000 [3:30:06<14:15:24,  1.71it/s]
Train steps ... :  12%|█▏        | 12208/100000 [3:30:07<14:15:33,  1.71it/s]
Train steps ... :  12%|█▏        | 12209/100000 [3:30:08<14:15:42,  1.71it/s]
Train steps ... :  12%|█▏        | 12210/100000 [3:30:08<14:15:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12211/100000 [3:30:09<14:14:53,  1.71it/s]
Train steps ... :  12%|█▏        | 12212/100000 [3:30:09<14:15:51,  1.71it/s]
Train steps ... :  12%|█▏        | 12213/100000 [3:30:10<14:15:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12214/100000 [3:30:10<14:14:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12215/100000 [3:30:11<14:14:48,  1.71it/s]
Train steps ... :  12%|█▏        | 12216/100000 [3:30:12<14:15:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12217/100000 [3:30:12<14:15:36,  1.71it/s]
Train steps ... :  12%|█▏        | 12218/100000 [3:30:13<14:15:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12219/100000 [3:30:13<14:14:41,  1.71it/s]
Train steps ... :  12%|█▏        | 12220/100000 [3:30:14<14:16:32,  1.71it/s]
Train steps ... :  12%|█▏        | 12221/100000 [3:30:15<14:14:48,  1.71it/s]
Train steps ... :  12%|█▏        | 12222/100000 [3:30:15<14:14:27,  1.71it/s]
Train steps ... :  12%|█▏        | 12223/100000 [3:30:16<14:14:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12224/100000 [3:30:16<14:14:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12225/100000 [3:30:17<14:14:12,  1.71it/s]Step... (12225 / 100000 | Loss: 1.283069372177124, Learning Rate: 8.821608040201007e-05)
+
                                                                             
Step... (12225 / 100000 | Loss: 1.0520321130752563, Learning Rate: 8.821608040201007e-05)
+
Train steps ... :  12%|█▏        | 12225/100000 [3:30:17<14:14:12,  1.71it/s]
Train steps ... :  12%|█▏        | 12226/100000 [3:30:17<14:14:36,  1.71it/s]
Train steps ... :  12%|█▏        | 12227/100000 [3:30:18<14:15:29,  1.71it/s]
Train steps ... :  12%|█▏        | 12228/100000 [3:30:19<14:15:39,  1.71it/s]
Train steps ... :  12%|█▏        | 12229/100000 [3:30:19<14:15:08,  1.71it/s]
Train steps ... :  12%|█▏        | 12230/100000 [3:30:20<14:14:57,  1.71it/s]
Train steps ... :  12%|█▏        | 12231/100000 [3:30:20<14:14:10,  1.71it/s]
Train steps ... :  12%|█▏        | 12232/100000 [3:30:21<14:14:40,  1.71it/s]
Train steps ... :  12%|█▏        | 12233/100000 [3:30:22<14:14:12,  1.71it/s]
Train steps ... :  12%|█▏        | 12234/100000 [3:30:22<14:14:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12235/100000 [3:30:23<14:14:38,  1.71it/s]
Train steps ... :  12%|█▏        | 12236/100000 [3:30:23<14:13:58,  1.71it/s]
Train steps ... :  12%|█▏        | 12237/100000 [3:30:24<14:14:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12238/100000 [3:30:24<14:14:31,  1.71it/s]
Train steps ... :  12%|█▏        | 12239/100000 [3:30:25<14:14:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12240/100000 [3:30:26<14:14:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12241/100000 [3:30:26<14:14:43,  1.71it/s]
Train steps ... :  12%|█▏        | 12242/100000 [3:30:27<14:15:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12243/100000 [3:30:27<14:15:27,  1.71it/s]
Train steps ... :  12%|█▏        | 12244/100000 [3:30:28<14:14:55,  1.71it/s]
Train steps ... :  12%|█▏        | 12245/100000 [3:30:29<14:15:05,  1.71it/s]
Train steps ... :  12%|█▏        | 12246/100000 [3:30:29<14:14:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12247/100000 [3:30:30<14:14:42,  1.71it/s]
Train steps ... :  12%|█▏        | 12248/100000 [3:30:30<14:15:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12249/100000 [3:30:31<14:14:22,  1.71it/s]
Train steps ... :  12%|█▏        | 12250/100000 [3:30:31<14:14:39,  1.71it/s]Step... (12250 / 100000 | Loss: 1.0356782674789429, Learning Rate: 8.819095477386935e-05)
+
                                                                             
Step... (12250 / 100000 | Loss: 1.1568262577056885, Learning Rate: 8.819095477386935e-05)
+
Train steps ... :  12%|█▏        | 12250/100000 [3:30:32<14:14:39,  1.71it/s]
Train steps ... :  12%|█▏        | 12251/100000 [3:30:32<14:16:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12252/100000 [3:30:33<14:15:14,  1.71it/s]
Train steps ... :  12%|█▏        | 12253/100000 [3:30:33<14:15:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12254/100000 [3:30:34<14:14:53,  1.71it/s]
Train steps ... :  12%|█▏        | 12255/100000 [3:30:34<14:17:41,  1.71it/s]
Train steps ... :  12%|█▏        | 12256/100000 [3:30:35<14:17:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12257/100000 [3:30:36<14:16:54,  1.71it/s]
Train steps ... :  12%|█▏        | 12258/100000 [3:30:36<14:15:43,  1.71it/s]
Train steps ... :  12%|█▏        | 12259/100000 [3:30:37<14:15:24,  1.71it/s]
Train steps ... :  12%|█▏        | 12260/100000 [3:30:37<14:15:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12261/100000 [3:30:38<14:15:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12262/100000 [3:30:39<14:15:03,  1.71it/s]
Train steps ... :  12%|█▏        | 12263/100000 [3:30:39<14:14:59,  1.71it/s]
Train steps ... :  12%|█▏        | 12264/100000 [3:30:40<14:17:06,  1.71it/s]
Train steps ... :  12%|█▏        | 12265/100000 [3:30:40<14:16:23,  1.71it/s]
Train steps ... :  12%|█▏        | 12266/100000 [3:30:41<14:15:37,  1.71it/s]
Train steps ... :  12%|█▏        | 12267/100000 [3:30:41<14:14:22,  1.71it/s]
Train steps ... :  12%|█▏        | 12268/100000 [3:30:42<14:14:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12269/100000 [3:30:43<14:14:42,  1.71it/s]
Train steps ... :  12%|█▏        | 12270/100000 [3:30:43<14:15:15,  1.71it/s]
Train steps ... :  12%|█▏        | 12271/100000 [3:30:44<14:13:33,  1.71it/s]
Train steps ... :  12%|█▏        | 12272/100000 [3:30:44<14:14:55,  1.71it/s]
Train steps ... :  12%|█▏        | 12273/100000 [3:30:45<14:16:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12274/100000 [3:30:46<14:14:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12275/100000 [3:30:46<14:14:04,  1.71it/s]Step... (12275 / 100000 | Loss: 1.1756964921951294, Learning Rate: 8.816582914572865e-05)
+
                                                                             
Step... (12275 / 100000 | Loss: 0.8742557764053345, Learning Rate: 8.816582914572865e-05)
+
Train steps ... :  12%|█▏        | 12275/100000 [3:30:46<14:14:04,  1.71it/s]
Train steps ... :  12%|█▏        | 12276/100000 [3:30:47<14:15:18,  1.71it/s]
Train steps ... :  12%|█▏        | 12277/100000 [3:30:47<14:14:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12278/100000 [3:30:48<14:14:35,  1.71it/s]
Train steps ... :  12%|█▏        | 12279/100000 [3:30:48<14:15:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12280/100000 [3:30:49<14:15:10,  1.71it/s]
Train steps ... :  12%|█▏        | 12281/100000 [3:30:50<14:15:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12282/100000 [3:30:50<14:15:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12283/100000 [3:30:51<14:15:06,  1.71it/s]
Train steps ... :  12%|█▏        | 12284/100000 [3:30:51<14:14:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12285/100000 [3:30:52<14:14:19,  1.71it/s]
Train steps ... :  12%|█▏        | 12286/100000 [3:30:53<14:14:32,  1.71it/s]
Train steps ... :  12%|█▏        | 12287/100000 [3:30:53<14:14:26,  1.71it/s]
Train steps ... :  12%|█▏        | 12288/100000 [3:30:54<14:13:51,  1.71it/s]
Train steps ... :  12%|█▏        | 12289/100000 [3:30:54<14:14:44,  1.71it/s]
Train steps ... :  12%|█▏        | 12290/100000 [3:30:55<14:14:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12291/100000 [3:30:55<14:15:08,  1.71it/s]
Train steps ... :  12%|█▏        | 12292/100000 [3:30:56<14:14:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12293/100000 [3:30:57<14:14:35,  1.71it/s]
Train steps ... :  12%|█▏        | 12294/100000 [3:30:57<14:15:10,  1.71it/s]
Train steps ... :  12%|█▏        | 12295/100000 [3:30:58<14:15:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12296/100000 [3:30:58<14:15:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12297/100000 [3:30:59<14:16:58,  1.71it/s]
Train steps ... :  12%|█▏        | 12298/100000 [3:31:00<14:15:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12299/100000 [3:31:00<14:15:14,  1.71it/s]
Train steps ... :  12%|█▏        | 12300/100000 [3:31:01<14:15:14,  1.71it/s]Step... (12300 / 100000 | Loss: 1.019288420677185, Learning Rate: 8.814070351758794e-05)
+
                                                                             
Step... (12300 / 100000 | Loss: 1.1448795795440674, Learning Rate: 8.814070351758794e-05)
+
Train steps ... :  12%|█▏        | 12300/100000 [3:31:01<14:15:14,  1.71it/s]
Train steps ... :  12%|█▏        | 12301/100000 [3:31:01<14:14:38,  1.71it/s]
Train steps ... :  12%|█▏        | 12302/100000 [3:31:02<14:13:28,  1.71it/s]
Train steps ... :  12%|█▏        | 12303/100000 [3:31:02<14:13:50,  1.71it/s]
Train steps ... :  12%|█▏        | 12304/100000 [3:31:03<14:15:03,  1.71it/s]
Train steps ... :  12%|█▏        | 12305/100000 [3:31:04<14:15:32,  1.71it/s]
Train steps ... :  12%|█▏        | 12306/100000 [3:31:04<14:15:45,  1.71it/s]
Train steps ... :  12%|█▏        | 12307/100000 [3:31:05<14:15:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12308/100000 [3:31:05<14:14:15,  1.71it/s]
Train steps ... :  12%|█▏        | 12309/100000 [3:31:06<14:13:47,  1.71it/s]
Train steps ... :  12%|█▏        | 12310/100000 [3:31:07<14:13:42,  1.71it/s]
Train steps ... :  12%|█▏        | 12311/100000 [3:31:07<14:13:58,  1.71it/s]
Train steps ... :  12%|█▏        | 12312/100000 [3:31:08<14:13:22,  1.71it/s]
Train steps ... :  12%|█▏        | 12313/100000 [3:31:08<14:13:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12314/100000 [3:31:09<14:12:58,  1.71it/s]
Train steps ... :  12%|█▏        | 12315/100000 [3:31:10<14:12:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12316/100000 [3:31:10<14:13:11,  1.71it/s]
Train steps ... :  12%|█▏        | 12317/100000 [3:31:11<14:13:24,  1.71it/s]
Train steps ... :  12%|█▏        | 12318/100000 [3:31:11<14:14:04,  1.71it/s]
Train steps ... :  12%|█▏        | 12319/100000 [3:31:12<14:13:47,  1.71it/s]
Train steps ... :  12%|█▏        | 12320/100000 [3:31:12<14:13:44,  1.71it/s]
Train steps ... :  12%|█▏        | 12321/100000 [3:31:13<14:14:42,  1.71it/s]
Train steps ... :  12%|█▏        | 12322/100000 [3:31:14<14:15:04,  1.71it/s]
Train steps ... :  12%|█▏        | 12323/100000 [3:31:14<14:16:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12324/100000 [3:31:15<14:16:26,  1.71it/s]
Train steps ... :  12%|█▏        | 12325/100000 [3:31:15<14:14:17,  1.71it/s]Step... (12325 / 100000 | Loss: 1.719814419746399, Learning Rate: 8.811557788944724e-05)
+
                                                                             
Step... (12325 / 100000 | Loss: 1.170743703842163, Learning Rate: 8.811557788944724e-05)
+
Train steps ... :  12%|█▏        | 12325/100000 [3:31:16<14:14:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12326/100000 [3:31:16<14:15:08,  1.71it/s]
Train steps ... :  12%|█▏        | 12327/100000 [3:31:17<14:15:06,  1.71it/s]
Train steps ... :  12%|█▏        | 12328/100000 [3:31:17<14:14:35,  1.71it/s]
Train steps ... :  12%|█▏        | 12329/100000 [3:31:18<14:13:44,  1.71it/s]
Train steps ... :  12%|█▏        | 12330/100000 [3:31:18<14:13:29,  1.71it/s]
Train steps ... :  12%|█▏        | 12331/100000 [3:31:19<14:13:06,  1.71it/s]
Train steps ... :  12%|█▏        | 12332/100000 [3:31:19<14:13:12,  1.71it/s]
Train steps ... :  12%|█▏        | 12333/100000 [3:31:20<14:13:04,  1.71it/s]
Train steps ... :  12%|█▏        | 12334/100000 [3:31:21<14:13:05,  1.71it/s]
Train steps ... :  12%|█▏        | 12335/100000 [3:31:21<14:14:37,  1.71it/s]
Train steps ... :  12%|█▏        | 12336/100000 [3:31:22<14:13:54,  1.71it/s]
Train steps ... :  12%|█▏        | 12337/100000 [3:31:22<14:14:23,  1.71it/s]
Train steps ... :  12%|█▏        | 12338/100000 [3:31:23<14:13:42,  1.71it/s]
Train steps ... :  12%|█▏        | 12339/100000 [3:31:24<14:14:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12340/100000 [3:31:24<14:14:55,  1.71it/s]
Train steps ... :  12%|█▏        | 12341/100000 [3:31:25<14:14:04,  1.71it/s]
Train steps ... :  12%|█▏        | 12342/100000 [3:31:25<14:13:37,  1.71it/s]
Train steps ... :  12%|█▏        | 12343/100000 [3:31:26<14:13:40,  1.71it/s]
Train steps ... :  12%|█▏        | 12344/100000 [3:31:26<14:13:51,  1.71it/s]
Train steps ... :  12%|█▏        | 12345/100000 [3:31:27<14:13:24,  1.71it/s]
Train steps ... :  12%|█▏        | 12346/100000 [3:31:28<14:13:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12347/100000 [3:31:28<14:13:19,  1.71it/s]
Train steps ... :  12%|█▏        | 12348/100000 [3:31:29<14:13:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12349/100000 [3:31:29<14:13:18,  1.71it/s]
Train steps ... :  12%|█▏        | 12350/100000 [3:31:30<14:14:49,  1.71it/s]Step... (12350 / 100000 | Loss: 1.3639264106750488, Learning Rate: 8.809045226130654e-05)
+
                                                                             
Step... (12350 / 100000 | Loss: 1.3658897876739502, Learning Rate: 8.809045226130654e-05)
+
Train steps ... :  12%|█▏        | 12350/100000 [3:31:30<14:14:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12351/100000 [3:31:31<14:14:18,  1.71it/s]
Train steps ... :  12%|█▏        | 12352/100000 [3:31:31<14:13:54,  1.71it/s]
Train steps ... :  12%|█▏        | 12353/100000 [3:31:32<14:13:48,  1.71it/s]
Train steps ... :  12%|█▏        | 12354/100000 [3:31:32<14:13:40,  1.71it/s]
Train steps ... :  12%|█▏        | 12355/100000 [3:31:33<14:15:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12356/100000 [3:31:33<14:16:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12357/100000 [3:31:34<14:15:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12358/100000 [3:31:35<14:15:54,  1.71it/s]
Train steps ... :  12%|█▏        | 12359/100000 [3:31:35<14:14:44,  1.71it/s]
Train steps ... :  12%|█▏        | 12360/100000 [3:31:36<14:13:48,  1.71it/s]
Train steps ... :  12%|█▏        | 12361/100000 [3:31:36<14:14:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12362/100000 [3:31:37<14:14:11,  1.71it/s]
Train steps ... :  12%|█▏        | 12363/100000 [3:31:38<14:14:10,  1.71it/s]
Train steps ... :  12%|█▏        | 12364/100000 [3:31:38<14:13:00,  1.71it/s]
Train steps ... :  12%|█▏        | 12365/100000 [3:31:39<14:13:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12366/100000 [3:31:39<14:13:01,  1.71it/s]
Train steps ... :  12%|█▏        | 12367/100000 [3:31:40<14:14:03,  1.71it/s]
Train steps ... :  12%|█▏        | 12368/100000 [3:31:40<14:13:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12369/100000 [3:31:41<14:14:30,  1.71it/s]
Train steps ... :  12%|█▏        | 12370/100000 [3:31:42<14:14:48,  1.71it/s]
Train steps ... :  12%|█▏        | 12371/100000 [3:31:42<14:14:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12372/100000 [3:31:43<14:13:51,  1.71it/s]
Train steps ... :  12%|█▏        | 12373/100000 [3:31:43<14:14:21,  1.71it/s]
Train steps ... :  12%|█▏        | 12374/100000 [3:31:44<14:14:01,  1.71it/s]
Train steps ... :  12%|█▏        | 12375/100000 [3:31:45<14:13:44,  1.71it/s]Step... (12375 / 100000 | Loss: 1.053048849105835, Learning Rate: 8.806532663316583e-05)
+
                                                                             
Step... (12375 / 100000 | Loss: 1.5358457565307617, Learning Rate: 8.806532663316583e-05)
+
Train steps ... :  12%|█▏        | 12375/100000 [3:31:45<14:13:44,  1.71it/s]
Train steps ... :  12%|█▏        | 12376/100000 [3:31:45<14:15:01,  1.71it/s]
Train steps ... :  12%|█▏        | 12377/100000 [3:31:46<14:13:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12378/100000 [3:31:46<14:14:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12379/100000 [3:31:47<14:13:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12380/100000 [3:31:48<14:13:11,  1.71it/s]
Train steps ... :  12%|█▏        | 12381/100000 [3:31:48<14:13:15,  1.71it/s]
Train steps ... :  12%|█▏        | 12382/100000 [3:31:49<14:14:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12383/100000 [3:31:49<14:13:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12384/100000 [3:31:50<14:14:31,  1.71it/s]
Train steps ... :  12%|█▏        | 12385/100000 [3:31:50<14:13:54,  1.71it/s]
Train steps ... :  12%|█▏        | 12386/100000 [3:31:51<14:13:21,  1.71it/s]
Train steps ... :  12%|█▏        | 12387/100000 [3:31:52<14:14:03,  1.71it/s]
Train steps ... :  12%|█▏        | 12388/100000 [3:31:52<14:12:57,  1.71it/s]
Train steps ... :  12%|█▏        | 12389/100000 [3:31:53<14:13:01,  1.71it/s]
Train steps ... :  12%|█▏        | 12390/100000 [3:31:53<14:13:28,  1.71it/s]
Train steps ... :  12%|█▏        | 12391/100000 [3:31:54<14:12:47,  1.71it/s]
Train steps ... :  12%|█▏        | 12392/100000 [3:31:55<14:14:05,  1.71it/s]
Train steps ... :  12%|█▏        | 12393/100000 [3:31:55<14:13:58,  1.71it/s]
Train steps ... :  12%|█▏        | 12394/100000 [3:31:56<14:13:37,  1.71it/s]
Train steps ... :  12%|█▏        | 12395/100000 [3:31:56<14:12:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12396/100000 [3:31:57<14:12:41,  1.71it/s]
Train steps ... :  12%|█▏        | 12397/100000 [3:31:57<14:12:33,  1.71it/s]
Train steps ... :  12%|█▏        | 12398/100000 [3:31:58<14:12:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12399/100000 [3:31:59<14:12:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12400/100000 [3:31:59<14:13:00,  1.71it/s]Step... (12400 / 100000 | Loss: 1.1097558736801147, Learning Rate: 8.804020100502513e-05)
+
                                                                             
Step... (12400 / 100000 | Loss: 0.9829684495925903, Learning Rate: 8.804020100502513e-05)
+
Train steps ... :  12%|█▏        | 12400/100000 [3:32:00<14:13:00,  1.71it/s]
Train steps ... :  12%|█▏        | 12401/100000 [3:32:00<14:13:10,  1.71it/s]
Train steps ... :  12%|█▏        | 12402/100000 [3:32:00<14:13:04,  1.71it/s]
Train steps ... :  12%|█▏        | 12403/100000 [3:32:01<14:12:45,  1.71it/s]
Train steps ... :  12%|█▏        | 12404/100000 [3:32:02<14:12:30,  1.71it/s]
Train steps ... :  12%|█▏        | 12405/100000 [3:32:02<14:12:06,  1.71it/s]
Train steps ... :  12%|█▏        | 12406/100000 [3:32:03<14:13:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12407/100000 [3:32:03<14:12:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12408/100000 [3:32:04<14:13:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12409/100000 [3:32:04<14:13:27,  1.71it/s]
Train steps ... :  12%|█▏        | 12410/100000 [3:32:05<14:14:05,  1.71it/s]
Train steps ... :  12%|█▏        | 12411/100000 [3:32:06<14:14:50,  1.71it/s]
Train steps ... :  12%|█▏        | 12412/100000 [3:32:06<14:13:58,  1.71it/s]
Train steps ... :  12%|█▏        | 12413/100000 [3:32:07<14:14:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12414/100000 [3:32:07<14:13:59,  1.71it/s]
Train steps ... :  12%|█▏        | 12415/100000 [3:32:08<14:13:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12416/100000 [3:32:09<14:14:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12417/100000 [3:32:09<14:12:31,  1.71it/s]
Train steps ... :  12%|█▏        | 12418/100000 [3:32:10<14:12:44,  1.71it/s]
Train steps ... :  12%|█▏        | 12419/100000 [3:32:10<14:12:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12420/100000 [3:32:11<14:12:27,  1.71it/s]
Train steps ... :  12%|█▏        | 12421/100000 [3:32:11<14:12:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12422/100000 [3:32:12<14:11:59,  1.71it/s]
Train steps ... :  12%|█▏        | 12423/100000 [3:32:13<14:12:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12424/100000 [3:32:13<14:12:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12425/100000 [3:32:14<14:11:52,  1.71it/s]Step... (12425 / 100000 | Loss: 1.0707452297210693, Learning Rate: 8.801507537688443e-05)
+
                                                                             
Step... (12425 / 100000 | Loss: 1.362175703048706, Learning Rate: 8.801507537688443e-05)
+
Train steps ... :  12%|█▏        | 12425/100000 [3:32:14<14:11:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12426/100000 [3:32:14<14:13:06,  1.71it/s]
Train steps ... :  12%|█▏        | 12427/100000 [3:32:15<14:12:38,  1.71it/s]
Train steps ... :  12%|█▏        | 12428/100000 [3:32:16<14:12:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12429/100000 [3:32:16<14:12:11,  1.71it/s]
Train steps ... :  12%|█▏        | 12430/100000 [3:32:17<14:14:28,  1.71it/s]
Train steps ... :  12%|█▏        | 12431/100000 [3:32:17<14:16:02,  1.70it/s]
Train steps ... :  12%|█▏        | 12432/100000 [3:32:18<14:15:53,  1.71it/s]
Train steps ... :  12%|█▏        | 12433/100000 [3:32:18<14:14:53,  1.71it/s]
Train steps ... :  12%|█▏        | 12434/100000 [3:32:19<14:13:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12435/100000 [3:32:20<14:13:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12436/100000 [3:32:20<14:13:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12437/100000 [3:32:21<14:14:03,  1.71it/s]
Train steps ... :  12%|█▏        | 12438/100000 [3:32:21<14:13:58,  1.71it/s]
Train steps ... :  12%|█▏        | 12439/100000 [3:32:22<14:14:25,  1.71it/s]
Train steps ... :  12%|█▏        | 12440/100000 [3:32:23<14:13:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12441/100000 [3:32:23<14:14:06,  1.71it/s]
Train steps ... :  12%|█▏        | 12442/100000 [3:32:24<14:13:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12443/100000 [3:32:24<14:13:50,  1.71it/s]
Train steps ... :  12%|█▏        | 12444/100000 [3:32:25<14:14:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12445/100000 [3:32:26<14:14:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12446/100000 [3:32:26<14:13:33,  1.71it/s]
Train steps ... :  12%|█▏        | 12447/100000 [3:32:27<14:13:05,  1.71it/s]
Train steps ... :  12%|█▏        | 12448/100000 [3:32:27<14:12:52,  1.71it/s]
Train steps ... :  12%|█▏        | 12449/100000 [3:32:28<14:12:43,  1.71it/s]
Train steps ... :  12%|█▏        | 12450/100000 [3:32:28<14:12:39,  1.71it/s]Step... (12450 / 100000 | Loss: 1.2525767087936401, Learning Rate: 8.798994974874372e-05)
+
                                                                             
Step... (12450 / 100000 | Loss: 1.4186292886734009, Learning Rate: 8.798994974874372e-05)
+
Train steps ... :  12%|█▏        | 12450/100000 [3:32:29<14:12:39,  1.71it/s]
Train steps ... :  12%|█▏        | 12451/100000 [3:32:29<14:13:49,  1.71it/s]
Train steps ... :  12%|█▏        | 12452/100000 [3:32:30<14:13:46,  1.71it/s]
Train steps ... :  12%|█▏        | 12453/100000 [3:32:30<14:14:43,  1.71it/s]
Train steps ... :  12%|█▏        | 12454/100000 [3:32:31<14:14:35,  1.71it/s]
Train steps ... :  12%|█▏        | 12455/100000 [3:32:31<14:13:53,  1.71it/s]
Train steps ... :  12%|█▏        | 12456/100000 [3:32:32<14:14:31,  1.71it/s]
Train steps ... :  12%|█▏        | 12457/100000 [3:32:33<14:13:21,  1.71it/s]
Train steps ... :  12%|█▏        | 12458/100000 [3:32:33<14:13:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12459/100000 [3:32:34<14:13:15,  1.71it/s]
Train steps ... :  12%|█▏        | 12460/100000 [3:32:34<14:13:51,  1.71it/s]
Train steps ... :  12%|█▏        | 12461/100000 [3:32:35<14:14:04,  1.71it/s]
Train steps ... :  12%|█▏        | 12462/100000 [3:32:35<14:13:10,  1.71it/s]
Train steps ... :  12%|█▏        | 12463/100000 [3:32:36<14:13:27,  1.71it/s]
Train steps ... :  12%|█▏        | 12464/100000 [3:32:37<14:14:00,  1.71it/s]
Train steps ... :  12%|█▏        | 12465/100000 [3:32:37<14:13:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12466/100000 [3:32:38<14:13:07,  1.71it/s]
Train steps ... :  12%|█▏        | 12467/100000 [3:32:38<14:12:53,  1.71it/s]
Train steps ... :  12%|█▏        | 12468/100000 [3:32:39<14:12:37,  1.71it/s]
Train steps ... :  12%|█▏        | 12469/100000 [3:32:40<14:12:18,  1.71it/s]
Train steps ... :  12%|█▏        | 12470/100000 [3:32:40<14:12:17,  1.71it/s]
Train steps ... :  12%|█▏        | 12471/100000 [3:32:41<14:12:05,  1.71it/s]
Train steps ... :  12%|█▏        | 12472/100000 [3:32:41<14:11:48,  1.71it/s]
Train steps ... :  12%|█▏        | 12473/100000 [3:32:42<14:11:13,  1.71it/s]
Train steps ... :  12%|█▏        | 12474/100000 [3:32:42<14:11:08,  1.71it/s]
Train steps ... :  12%|█▏        | 12475/100000 [3:32:43<14:11:20,  1.71it/s]Step... (12475 / 100000 | Loss: 1.4229687452316284, Learning Rate: 8.796482412060302e-05)
+
                                                                             
Step... (12475 / 100000 | Loss: 1.0928113460540771, Learning Rate: 8.796482412060302e-05)
+
Train steps ... :  12%|█▏        | 12475/100000 [3:32:43<14:11:20,  1.71it/s]
Train steps ... :  12%|█▏        | 12476/100000 [3:32:44<14:11:32,  1.71it/s]
Train steps ... :  12%|█▏        | 12477/100000 [3:32:44<14:11:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12478/100000 [3:32:45<14:11:47,  1.71it/s]
Train steps ... :  12%|█▏        | 12479/100000 [3:32:45<14:11:56,  1.71it/s]
Train steps ... :  12%|█▏        | 12480/100000 [3:32:46<14:12:31,  1.71it/s]
Train steps ... :  12%|█▏        | 12481/100000 [3:32:47<14:12:03,  1.71it/s]
Train steps ... :  12%|█▏        | 12482/100000 [3:32:47<14:12:42,  1.71it/s]
Train steps ... :  12%|█▏        | 12483/100000 [3:32:48<14:12:33,  1.71it/s]
Train steps ... :  12%|█▏        | 12484/100000 [3:32:48<14:12:09,  1.71it/s]
Train steps ... :  12%|█▏        | 12485/100000 [3:32:49<14:11:55,  1.71it/s]
Train steps ... :  12%|█▏        | 12486/100000 [3:32:49<14:11:21,  1.71it/s]
Train steps ... :  12%|█▏        | 12487/100000 [3:32:50<14:11:43,  1.71it/s]
Train steps ... :  12%|█▏        | 12488/100000 [3:32:51<14:11:37,  1.71it/s]
Train steps ... :  12%|█▏        | 12489/100000 [3:32:51<14:13:11,  1.71it/s]
Train steps ... :  12%|█▏        | 12490/100000 [3:32:52<14:13:40,  1.71it/s]
Train steps ... :  12%|█▏        | 12491/100000 [3:32:52<14:13:02,  1.71it/s]
Train steps ... :  12%|█▏        | 12492/100000 [3:32:53<14:13:31,  1.71it/s]
Train steps ... :  12%|█▏        | 12493/100000 [3:32:54<14:15:01,  1.71it/s]
Train steps ... :  12%|█▏        | 12494/100000 [3:32:54<14:12:31,  1.71it/s]
Train steps ... :  12%|█▏        | 12495/100000 [3:32:55<14:11:39,  1.71it/s]
Train steps ... :  12%|█▏        | 12496/100000 [3:32:55<14:11:06,  1.71it/s]
Train steps ... :  12%|█▏        | 12497/100000 [3:32:56<14:11:16,  1.71it/s]
Train steps ... :  12%|█▏        | 12498/100000 [3:32:56<14:12:34,  1.71it/s]
Train steps ... :  12%|█▏        | 12499/100000 [3:32:57<14:12:05,  1.71it/s]
Train steps ... :  12%|█▎        | 12500/100000 [3:32:58<14:11:28,  1.71it/s]Step... (12500 / 100000 | Loss: 1.0535000562667847, Learning Rate: 8.793969849246232e-05)
+
                                                                             
Step... (12500 / 100000 | Loss: 1.507070779800415, Learning Rate: 8.793969849246232e-05)
+
Train steps ... :  12%|█▎        | 12500/100000 [3:32:58<14:11:28,  1.71it/s]
Train steps ... :  13%|█▎        | 12501/100000 [3:32:58<14:12:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12502/100000 [3:32:59<14:13:19,  1.71it/s]
Train steps ... :  13%|█▎        | 12503/100000 [3:32:59<14:12:28,  1.71it/s]
Train steps ... :  13%|█▎        | 12504/100000 [3:33:00<14:12:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12505/100000 [3:33:01<14:11:47,  1.71it/s]
Train steps ... :  13%|█▎        | 12506/100000 [3:33:01<14:11:54,  1.71it/s]
Train steps ... :  13%|█▎        | 12507/100000 [3:33:02<14:11:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12508/100000 [3:33:02<14:12:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12509/100000 [3:33:03<14:11:08,  1.71it/s]
Train steps ... :  13%|█▎        | 12510/100000 [3:33:04<14:11:28,  1.71it/s]
Train steps ... :  13%|█▎        | 12511/100000 [3:33:04<14:11:27,  1.71it/s]
Train steps ... :  13%|█▎        | 12512/100000 [3:33:05<14:11:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12513/100000 [3:33:05<14:11:25,  1.71it/s]
Train steps ... :  13%|█▎        | 12514/100000 [3:33:06<14:11:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12515/100000 [3:33:06<14:10:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12516/100000 [3:33:07<14:11:39,  1.71it/s]
Train steps ... :  13%|█▎        | 12517/100000 [3:33:08<14:11:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12518/100000 [3:33:08<14:12:25,  1.71it/s]
Train steps ... :  13%|█▎        | 12519/100000 [3:33:09<14:12:06,  1.71it/s]
Train steps ... :  13%|█▎        | 12520/100000 [3:33:09<14:12:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12521/100000 [3:33:10<14:11:36,  1.71it/s]
Train steps ... :  13%|█▎        | 12522/100000 [3:33:11<14:12:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12523/100000 [3:33:11<14:12:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12524/100000 [3:33:12<14:12:13,  1.71it/s]
Train steps ... :  13%|█▎        | 12525/100000 [3:33:12<14:12:13,  1.71it/s]Step... (12525 / 100000 | Loss: 0.8511216640472412, Learning Rate: 8.791457286432161e-05)
+
                                                                             
Step... (12525 / 100000 | Loss: 1.1089704036712646, Learning Rate: 8.791457286432161e-05)
+
Train steps ... :  13%|█▎        | 12525/100000 [3:33:13<14:12:13,  1.71it/s]
Train steps ... :  13%|█▎        | 12526/100000 [3:33:13<14:12:23,  1.71it/s]
Train steps ... :  13%|█▎        | 12527/100000 [3:33:13<14:12:48,  1.71it/s]
Train steps ... :  13%|█▎        | 12528/100000 [3:33:14<14:12:50,  1.71it/s]
Train steps ... :  13%|█▎        | 12529/100000 [3:33:15<14:12:12,  1.71it/s]
Train steps ... :  13%|█▎        | 12530/100000 [3:33:15<14:11:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12531/100000 [3:33:16<14:12:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12532/100000 [3:33:16<14:11:18,  1.71it/s]
Train steps ... :  13%|█▎        | 12533/100000 [3:33:17<14:11:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12534/100000 [3:33:18<14:12:15,  1.71it/s]
Train steps ... :  13%|█▎        | 12535/100000 [3:33:18<14:12:47,  1.71it/s]
Train steps ... :  13%|█▎        | 12536/100000 [3:33:19<14:12:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12537/100000 [3:33:19<14:11:55,  1.71it/s]
Train steps ... :  13%|█▎        | 12538/100000 [3:33:20<14:11:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12539/100000 [3:33:20<14:11:18,  1.71it/s]
Train steps ... :  13%|█▎        | 12540/100000 [3:33:21<14:11:06,  1.71it/s]
Train steps ... :  13%|█▎        | 12541/100000 [3:33:22<14:11:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12542/100000 [3:33:22<14:12:06,  1.71it/s]
Train steps ... :  13%|█▎        | 12543/100000 [3:33:23<14:10:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12544/100000 [3:33:23<14:11:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12545/100000 [3:33:24<14:11:37,  1.71it/s]
Train steps ... :  13%|█▎        | 12546/100000 [3:33:25<14:13:41,  1.71it/s]
Train steps ... :  13%|█▎        | 12547/100000 [3:33:25<14:13:48,  1.71it/s]
Train steps ... :  13%|█▎        | 12548/100000 [3:33:26<14:12:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12549/100000 [3:33:26<14:12:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12550/100000 [3:33:27<14:12:02,  1.71it/s]Step... (12550 / 100000 | Loss: 1.4206228256225586, Learning Rate: 8.788944723618091e-05)
+
                                                                             
Step... (12550 / 100000 | Loss: 1.435411810874939, Learning Rate: 8.788944723618091e-05)
+
Train steps ... :  13%|█▎        | 12550/100000 [3:33:27<14:12:02,  1.71it/s]
Train steps ... :  13%|█▎        | 12551/100000 [3:33:27<14:12:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12552/100000 [3:33:28<14:12:35,  1.71it/s]
Train steps ... :  13%|█▎        | 12553/100000 [3:33:29<14:12:52,  1.71it/s]
Train steps ... :  13%|█▎        | 12554/100000 [3:33:29<14:12:45,  1.71it/s]
Train steps ... :  13%|█▎        | 12555/100000 [3:33:30<14:12:12,  1.71it/s]
Train steps ... :  13%|█▎        | 12556/100000 [3:33:30<14:12:06,  1.71it/s]
Train steps ... :  13%|█▎        | 12557/100000 [3:33:31<14:11:55,  1.71it/s]
Train steps ... :  13%|█▎        | 12558/100000 [3:33:32<14:13:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12559/100000 [3:33:32<14:12:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12560/100000 [3:33:33<14:13:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12561/100000 [3:33:33<14:12:09,  1.71it/s]
Train steps ... :  13%|█▎        | 12562/100000 [3:33:34<14:11:57,  1.71it/s]
Train steps ... :  13%|█▎        | 12563/100000 [3:33:34<14:11:16,  1.71it/s]
Train steps ... :  13%|█▎        | 12564/100000 [3:33:35<14:12:02,  1.71it/s]
Train steps ... :  13%|█▎        | 12565/100000 [3:33:36<14:11:33,  1.71it/s]
Train steps ... :  13%|█▎        | 12566/100000 [3:33:36<14:11:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12567/100000 [3:33:37<14:12:34,  1.71it/s]
Train steps ... :  13%|█▎        | 12568/100000 [3:33:37<14:12:15,  1.71it/s]
Train steps ... :  13%|█▎        | 12569/100000 [3:33:38<14:12:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12570/100000 [3:33:39<14:12:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12571/100000 [3:33:39<14:13:07,  1.71it/s]
Train steps ... :  13%|█▎        | 12572/100000 [3:33:40<14:12:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12573/100000 [3:33:40<14:12:36,  1.71it/s]
Train steps ... :  13%|█▎        | 12574/100000 [3:33:41<14:13:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12575/100000 [3:33:42<14:11:59,  1.71it/s]Step... (12575 / 100000 | Loss: 1.090461254119873, Learning Rate: 8.78643216080402e-05)
+
                                                                             
Step... (12575 / 100000 | Loss: 1.139784336090088, Learning Rate: 8.78643216080402e-05)
+
Train steps ... :  13%|█▎        | 12575/100000 [3:33:42<14:11:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12576/100000 [3:33:42<14:12:20,  1.71it/s]
Train steps ... :  13%|█▎        | 12577/100000 [3:33:43<14:12:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12578/100000 [3:33:43<14:12:04,  1.71it/s]
Train steps ... :  13%|█▎        | 12579/100000 [3:33:44<14:11:46,  1.71it/s]
Train steps ... :  13%|█▎        | 12580/100000 [3:33:44<14:11:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12581/100000 [3:33:45<14:11:18,  1.71it/s]
Train steps ... :  13%|█▎        | 12582/100000 [3:33:46<14:10:22,  1.71it/s]
Train steps ... :  13%|█▎        | 12583/100000 [3:33:46<14:11:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12584/100000 [3:33:47<14:10:50,  1.71it/s]
Train steps ... :  13%|█▎        | 12585/100000 [3:33:47<14:12:19,  1.71it/s]
Train steps ... :  13%|█▎        | 12586/100000 [3:33:48<14:11:37,  1.71it/s]
Train steps ... :  13%|█▎        | 12587/100000 [3:33:49<14:12:23,  1.71it/s]
Train steps ... :  13%|█▎        | 12588/100000 [3:33:49<14:11:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12589/100000 [3:33:50<14:11:48,  1.71it/s]
Train steps ... :  13%|█▎        | 12590/100000 [3:33:50<14:10:46,  1.71it/s]
Train steps ... :  13%|█▎        | 12591/100000 [3:33:51<14:11:39,  1.71it/s]
Train steps ... :  13%|█▎        | 12592/100000 [3:33:51<14:11:11,  1.71it/s]
Train steps ... :  13%|█▎        | 12593/100000 [3:33:52<14:11:07,  1.71it/s]
Train steps ... :  13%|█▎        | 12594/100000 [3:33:53<14:11:08,  1.71it/s]
Train steps ... :  13%|█▎        | 12595/100000 [3:33:53<14:10:36,  1.71it/s]
Train steps ... :  13%|█▎        | 12596/100000 [3:33:54<14:10:51,  1.71it/s]
Train steps ... :  13%|█▎        | 12597/100000 [3:33:54<14:10:52,  1.71it/s]
Train steps ... :  13%|█▎        | 12598/100000 [3:33:55<14:11:45,  1.71it/s]
Train steps ... :  13%|█▎        | 12599/100000 [3:33:56<14:13:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12600/100000 [3:33:56<14:12:37,  1.71it/s]Step... (12600 / 100000 | Loss: 1.051762580871582, Learning Rate: 8.78391959798995e-05)
+
                                                                             
Step... (12600 / 100000 | Loss: 0.8674403429031372, Learning Rate: 8.78391959798995e-05)
+
Train steps ... :  13%|█▎        | 12600/100000 [3:33:56<14:12:37,  1.71it/s]
Train steps ... :  13%|█▎        | 12601/100000 [3:33:57<14:12:52,  1.71it/s]
Train steps ... :  13%|█▎        | 12602/100000 [3:33:57<14:12:09,  1.71it/s]
Train steps ... :  13%|█▎        | 12603/100000 [3:33:58<14:12:14,  1.71it/s]
Train steps ... :  13%|█▎        | 12604/100000 [3:33:58<14:12:41,  1.71it/s]
Train steps ... :  13%|█▎        | 12605/100000 [3:33:59<14:12:06,  1.71it/s]
Train steps ... :  13%|█▎        | 12606/100000 [3:34:00<14:12:13,  1.71it/s]
Train steps ... :  13%|█▎        | 12607/100000 [3:34:00<14:12:04,  1.71it/s]
Train steps ... :  13%|█▎        | 12608/100000 [3:34:01<14:11:19,  1.71it/s]
Train steps ... :  13%|█▎        | 12609/100000 [3:34:01<14:11:46,  1.71it/s]
Train steps ... :  13%|█▎        | 12610/100000 [3:34:02<14:11:46,  1.71it/s]
Train steps ... :  13%|█▎        | 12611/100000 [3:34:03<14:11:23,  1.71it/s]
Train steps ... :  13%|█▎        | 12612/100000 [3:34:03<14:11:08,  1.71it/s]
Train steps ... :  13%|█▎        | 12613/100000 [3:34:04<14:12:27,  1.71it/s]
Train steps ... :  13%|█▎        | 12614/100000 [3:34:04<14:12:54,  1.71it/s]
Train steps ... :  13%|█▎        | 12615/100000 [3:34:05<14:12:00,  1.71it/s]
Train steps ... :  13%|█▎        | 12616/100000 [3:34:05<14:11:31,  1.71it/s]
Train steps ... :  13%|█▎        | 12617/100000 [3:34:06<14:11:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12618/100000 [3:34:07<14:11:13,  1.71it/s]
Train steps ... :  13%|█▎        | 12619/100000 [3:34:07<14:12:23,  1.71it/s]
Train steps ... :  13%|█▎        | 12620/100000 [3:34:08<14:11:55,  1.71it/s]
Train steps ... :  13%|█▎        | 12621/100000 [3:34:08<14:11:22,  1.71it/s]
Train steps ... :  13%|█▎        | 12622/100000 [3:34:09<14:10:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12623/100000 [3:34:10<14:11:13,  1.71it/s]
Train steps ... :  13%|█▎        | 12624/100000 [3:34:10<14:10:37,  1.71it/s]
Train steps ... :  13%|█▎        | 12625/100000 [3:34:11<14:11:38,  1.71it/s]Step... (12625 / 100000 | Loss: 1.0591208934783936, Learning Rate: 8.78140703517588e-05)
+
                                                                             
Step... (12625 / 100000 | Loss: 1.0467915534973145, Learning Rate: 8.78140703517588e-05)
+
Train steps ... :  13%|█▎        | 12625/100000 [3:34:11<14:11:38,  1.71it/s]
Train steps ... :  13%|█▎        | 12626/100000 [3:34:11<14:11:36,  1.71it/s]
Train steps ... :  13%|█▎        | 12627/100000 [3:34:12<14:10:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12628/100000 [3:34:12<14:11:25,  1.71it/s]
Train steps ... :  13%|█▎        | 12629/100000 [3:34:13<14:11:15,  1.71it/s]
Train steps ... :  13%|█▎        | 12630/100000 [3:34:14<14:11:15,  1.71it/s]
Train steps ... :  13%|█▎        | 12631/100000 [3:34:14<14:11:12,  1.71it/s]
Train steps ... :  13%|█▎        | 12632/100000 [3:34:15<14:11:18,  1.71it/s]
Train steps ... :  13%|█▎        | 12633/100000 [3:34:15<14:12:16,  1.71it/s]
Train steps ... :  13%|█▎        | 12634/100000 [3:34:16<14:11:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12635/100000 [3:34:17<14:11:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12636/100000 [3:34:17<14:11:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12637/100000 [3:34:18<14:10:52,  1.71it/s]
Train steps ... :  13%|█▎        | 12638/100000 [3:34:18<14:12:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12639/100000 [3:34:19<14:10:33,  1.71it/s]
Train steps ... :  13%|█▎        | 12640/100000 [3:34:20<14:11:41,  1.71it/s]
Train steps ... :  13%|█▎        | 12641/100000 [3:34:20<14:11:07,  1.71it/s]
Train steps ... :  13%|█▎        | 12642/100000 [3:34:21<14:10:50,  1.71it/s]
Train steps ... :  13%|█▎        | 12643/100000 [3:34:21<14:11:26,  1.71it/s]
Train steps ... :  13%|█▎        | 12644/100000 [3:34:22<14:10:16,  1.71it/s]
Train steps ... :  13%|█▎        | 12645/100000 [3:34:22<14:11:04,  1.71it/s]
Train steps ... :  13%|█▎        | 12646/100000 [3:34:23<14:10:48,  1.71it/s]
Train steps ... :  13%|█▎        | 12647/100000 [3:34:24<14:10:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12648/100000 [3:34:24<14:11:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12649/100000 [3:34:25<14:10:57,  1.71it/s]
Train steps ... :  13%|█▎        | 12650/100000 [3:34:25<14:11:30,  1.71it/s]Step... (12650 / 100000 | Loss: 1.1773407459259033, Learning Rate: 8.77889447236181e-05)
+
                                                                             
Step... (12650 / 100000 | Loss: 0.9502462148666382, Learning Rate: 8.77889447236181e-05)
+
Train steps ... :  13%|█▎        | 12650/100000 [3:34:26<14:11:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12651/100000 [3:34:26<14:13:13,  1.71it/s]
Train steps ... :  13%|█▎        | 12652/100000 [3:34:27<14:12:15,  1.71it/s]
Train steps ... :  13%|█▎        | 12653/100000 [3:34:27<14:11:44,  1.71it/s]
Train steps ... :  13%|█▎        | 12654/100000 [3:34:28<14:10:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12655/100000 [3:34:28<14:11:50,  1.71it/s]
Train steps ... :  13%|█▎        | 12656/100000 [3:34:29<14:10:32,  1.71it/s]
Train steps ... :  13%|█▎        | 12657/100000 [3:34:29<14:10:42,  1.71it/s]
Train steps ... :  13%|█▎        | 12658/100000 [3:34:30<14:10:23,  1.71it/s]
Train steps ... :  13%|█▎        | 12659/100000 [3:34:31<14:10:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12660/100000 [3:34:31<14:10:08,  1.71it/s]
Train steps ... :  13%|█▎        | 12661/100000 [3:34:32<14:10:27,  1.71it/s]
Train steps ... :  13%|█▎        | 12662/100000 [3:34:32<14:10:33,  1.71it/s]
Train steps ... :  13%|█▎        | 12663/100000 [3:34:33<14:09:50,  1.71it/s]
Train steps ... :  13%|█▎        | 12664/100000 [3:34:34<14:09:45,  1.71it/s]
Train steps ... :  13%|█▎        | 12665/100000 [3:34:34<14:10:58,  1.71it/s]
Train steps ... :  13%|█▎        | 12666/100000 [3:34:35<14:11:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12667/100000 [3:34:35<14:10:55,  1.71it/s]
Train steps ... :  13%|█▎        | 12668/100000 [3:34:36<14:12:03,  1.71it/s]
Train steps ... :  13%|█▎        | 12669/100000 [3:34:36<14:12:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12670/100000 [3:34:37<14:12:28,  1.71it/s]
Train steps ... :  13%|█▎        | 12671/100000 [3:34:38<14:12:03,  1.71it/s]
Train steps ... :  13%|█▎        | 12672/100000 [3:34:38<14:11:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12673/100000 [3:34:39<14:11:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12674/100000 [3:34:39<14:10:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12675/100000 [3:34:40<14:10:49,  1.71it/s]Step... (12675 / 100000 | Loss: 1.1080262660980225, Learning Rate: 8.776381909547739e-05)
+
                                                                             
Step... (12675 / 100000 | Loss: 1.0898287296295166, Learning Rate: 8.776381909547739e-05)
+
Train steps ... :  13%|█▎        | 12675/100000 [3:34:40<14:10:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12676/100000 [3:34:41<14:11:05,  1.71it/s]
Train steps ... :  13%|█▎        | 12677/100000 [3:34:41<14:10:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12678/100000 [3:34:42<14:10:44,  1.71it/s]
Train steps ... :  13%|█▎        | 12679/100000 [3:34:42<14:09:38,  1.71it/s]
Train steps ... :  13%|█▎        | 12680/100000 [3:34:43<14:09:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12681/100000 [3:34:43<14:12:19,  1.71it/s]
Train steps ... :  13%|█▎        | 12682/100000 [3:34:44<14:10:44,  1.71it/s]
Train steps ... :  13%|█▎        | 12683/100000 [3:34:45<14:10:08,  1.71it/s]
Train steps ... :  13%|█▎        | 12684/100000 [3:34:45<14:10:25,  1.71it/s]
Train steps ... :  13%|█▎        | 12685/100000 [3:34:46<14:10:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12686/100000 [3:34:46<14:10:16,  1.71it/s]
Train steps ... :  13%|█▎        | 12687/100000 [3:34:47<14:09:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12688/100000 [3:34:48<14:09:29,  1.71it/s]
Train steps ... :  13%|█▎        | 12689/100000 [3:34:48<14:10:56,  1.71it/s]
Train steps ... :  13%|█▎        | 12690/100000 [3:34:49<14:10:03,  1.71it/s]
Train steps ... :  13%|█▎        | 12691/100000 [3:34:49<14:09:33,  1.71it/s]
Train steps ... :  13%|█▎        | 12692/100000 [3:34:50<14:10:04,  1.71it/s]
Train steps ... :  13%|█▎        | 12693/100000 [3:34:50<14:11:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12694/100000 [3:34:51<14:11:02,  1.71it/s]
Train steps ... :  13%|█▎        | 12695/100000 [3:34:52<14:10:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12696/100000 [3:34:52<14:10:41,  1.71it/s]
Train steps ... :  13%|█▎        | 12697/100000 [3:34:53<14:11:19,  1.71it/s]
Train steps ... :  13%|█▎        | 12698/100000 [3:34:53<14:10:46,  1.71it/s]
Train steps ... :  13%|█▎        | 12699/100000 [3:34:54<14:11:34,  1.71it/s]
Train steps ... :  13%|█▎        | 12700/100000 [3:34:55<14:10:33,  1.71it/s]Step... (12700 / 100000 | Loss: 1.2797937393188477, Learning Rate: 8.773869346733669e-05)
+
                                                                             
Step... (12700 / 100000 | Loss: 1.4405605792999268, Learning Rate: 8.773869346733669e-05)
+
Train steps ... :  13%|█▎        | 12700/100000 [3:34:55<14:10:33,  1.71it/s]
Train steps ... :  13%|█▎        | 12701/100000 [3:34:55<14:10:58,  1.71it/s]
Train steps ... :  13%|█▎        | 12702/100000 [3:34:56<14:10:31,  1.71it/s]
Train steps ... :  13%|█▎        | 12703/100000 [3:34:56<14:10:31,  1.71it/s]
Train steps ... :  13%|█▎        | 12704/100000 [3:34:57<14:09:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12705/100000 [3:34:58<14:10:36,  1.71it/s]
Train steps ... :  13%|█▎        | 12706/100000 [3:34:58<14:10:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12707/100000 [3:34:59<14:10:32,  1.71it/s]
Train steps ... :  13%|█▎        | 12708/100000 [3:34:59<14:11:23,  1.71it/s]
Train steps ... :  13%|█▎        | 12709/100000 [3:35:00<14:10:13,  1.71it/s]
Train steps ... :  13%|█▎        | 12710/100000 [3:35:00<14:10:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12711/100000 [3:35:01<14:10:25,  1.71it/s]
Train steps ... :  13%|█▎        | 12712/100000 [3:35:02<14:09:50,  1.71it/s]
Train steps ... :  13%|█▎        | 12713/100000 [3:35:02<14:09:57,  1.71it/s]
Train steps ... :  13%|█▎        | 12714/100000 [3:35:03<14:11:31,  1.71it/s]
Train steps ... :  13%|█▎        | 12715/100000 [3:35:03<14:11:04,  1.71it/s]
Train steps ... :  13%|█▎        | 12716/100000 [3:35:04<14:10:54,  1.71it/s]
Train steps ... :  13%|█▎        | 12717/100000 [3:35:05<14:11:05,  1.71it/s]
Train steps ... :  13%|█▎        | 12718/100000 [3:35:05<14:11:34,  1.71it/s]
Train steps ... :  13%|█▎        | 12719/100000 [3:35:06<14:10:42,  1.71it/s]
Train steps ... :  13%|█▎        | 12720/100000 [3:35:06<14:10:06,  1.71it/s]
Train steps ... :  13%|█▎        | 12721/100000 [3:35:07<14:09:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12722/100000 [3:35:07<14:09:28,  1.71it/s]
Train steps ... :  13%|█▎        | 12723/100000 [3:35:08<14:09:45,  1.71it/s]
Train steps ... :  13%|█▎        | 12724/100000 [3:35:09<14:09:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12725/100000 [3:35:09<14:10:36,  1.71it/s]Step... (12725 / 100000 | Loss: 1.1131460666656494, Learning Rate: 8.771356783919598e-05)
+
                                                                             
Step... (12725 / 100000 | Loss: 1.181300401687622, Learning Rate: 8.771356783919598e-05)
+
Train steps ... :  13%|█▎        | 12725/100000 [3:35:10<14:10:36,  1.71it/s]
Train steps ... :  13%|█▎        | 12726/100000 [3:35:10<14:11:19,  1.71it/s]
Train steps ... :  13%|█▎        | 12727/100000 [3:35:10<14:09:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12728/100000 [3:35:11<14:08:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12729/100000 [3:35:12<14:09:03,  1.71it/s]
Train steps ... :  13%|█▎        | 12730/100000 [3:35:12<14:11:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12731/100000 [3:35:13<14:12:02,  1.71it/s]
Train steps ... :  13%|█▎        | 12732/100000 [3:35:13<14:11:13,  1.71it/s]
Train steps ... :  13%|█▎        | 12733/100000 [3:35:14<14:10:14,  1.71it/s]
Train steps ... :  13%|█▎        | 12734/100000 [3:35:14<14:10:26,  1.71it/s]
Train steps ... :  13%|█▎        | 12735/100000 [3:35:15<14:10:58,  1.71it/s]
Train steps ... :  13%|█▎        | 12736/100000 [3:35:16<14:10:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12737/100000 [3:35:16<14:11:18,  1.71it/s]
Train steps ... :  13%|█▎        | 12738/100000 [3:35:17<14:10:23,  1.71it/s]
Train steps ... :  13%|█▎        | 12739/100000 [3:35:17<14:09:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12740/100000 [3:35:18<14:11:06,  1.71it/s]
Train steps ... :  13%|█▎        | 12741/100000 [3:35:19<14:09:28,  1.71it/s]
Train steps ... :  13%|█▎        | 12742/100000 [3:35:19<14:09:45,  1.71it/s]
Train steps ... :  13%|█▎        | 12743/100000 [3:35:20<14:11:00,  1.71it/s]
Train steps ... :  13%|█▎        | 12744/100000 [3:35:20<14:09:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12745/100000 [3:35:21<14:09:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12746/100000 [3:35:21<14:11:12,  1.71it/s]
Train steps ... :  13%|█▎        | 12747/100000 [3:35:22<14:10:06,  1.71it/s]
Train steps ... :  13%|█▎        | 12748/100000 [3:35:23<14:09:32,  1.71it/s]
Train steps ... :  13%|█▎        | 12749/100000 [3:35:23<14:09:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12750/100000 [3:35:24<14:10:20,  1.71it/s]Step... (12750 / 100000 | Loss: 0.8222498297691345, Learning Rate: 8.768844221105528e-05)
+
                                                                             
Step... (12750 / 100000 | Loss: 0.9847074747085571, Learning Rate: 8.768844221105528e-05)
+
Train steps ... :  13%|█▎        | 12750/100000 [3:35:24<14:10:20,  1.71it/s]
Train steps ... :  13%|█▎        | 12751/100000 [3:35:24<14:11:38,  1.71it/s]
Train steps ... :  13%|█▎        | 12752/100000 [3:35:25<14:11:04,  1.71it/s]
Train steps ... :  13%|█▎        | 12753/100000 [3:35:26<14:11:00,  1.71it/s]
Train steps ... :  13%|█▎        | 12754/100000 [3:35:26<14:11:12,  1.71it/s]
Train steps ... :  13%|█▎        | 12755/100000 [3:35:27<14:10:15,  1.71it/s]
Train steps ... :  13%|█▎        | 12756/100000 [3:35:27<14:09:51,  1.71it/s]
Train steps ... :  13%|█▎        | 12757/100000 [3:35:28<14:12:44,  1.71it/s]
Train steps ... :  13%|█▎        | 12758/100000 [3:35:29<14:09:47,  1.71it/s]
Train steps ... :  13%|█▎        | 12759/100000 [3:35:29<14:10:09,  1.71it/s]
Train steps ... :  13%|█▎        | 12760/100000 [3:35:30<14:10:35,  1.71it/s]
Train steps ... :  13%|█▎        | 12761/100000 [3:35:30<14:11:06,  1.71it/s]
Train steps ... :  13%|█▎        | 12762/100000 [3:35:31<14:12:25,  1.71it/s]
Train steps ... :  13%|█▎        | 12763/100000 [3:35:31<14:11:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12764/100000 [3:35:32<14:10:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12765/100000 [3:35:33<14:10:52,  1.71it/s]
Train steps ... :  13%|█▎        | 12766/100000 [3:35:33<14:11:22,  1.71it/s]
Train steps ... :  13%|█▎        | 12767/100000 [3:35:34<14:09:44,  1.71it/s]
Train steps ... :  13%|█▎        | 12768/100000 [3:35:34<14:10:08,  1.71it/s]
Train steps ... :  13%|█▎        | 12769/100000 [3:35:35<14:11:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12770/100000 [3:35:36<14:11:08,  1.71it/s]
Train steps ... :  13%|█▎        | 12771/100000 [3:35:36<14:10:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12772/100000 [3:35:37<14:10:35,  1.71it/s]
Train steps ... :  13%|█▎        | 12773/100000 [3:35:37<14:09:52,  1.71it/s]
Train steps ... :  13%|█▎        | 12774/100000 [3:35:38<14:09:55,  1.71it/s]
Train steps ... :  13%|█▎        | 12775/100000 [3:35:38<14:09:46,  1.71it/s]Step... (12775 / 100000 | Loss: 0.8671631813049316, Learning Rate: 8.766331658291458e-05)
+
                                                                             
Step... (12775 / 100000 | Loss: 0.981850266456604, Learning Rate: 8.766331658291458e-05)
+
Train steps ... :  13%|█▎        | 12775/100000 [3:35:39<14:09:46,  1.71it/s]
Train steps ... :  13%|█▎        | 12776/100000 [3:35:39<14:09:58,  1.71it/s]
Train steps ... :  13%|█▎        | 12777/100000 [3:35:40<14:09:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12778/100000 [3:35:40<14:09:35,  1.71it/s]
Train steps ... :  13%|█▎        | 12779/100000 [3:35:41<14:10:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12780/100000 [3:35:41<14:10:25,  1.71it/s]
Train steps ... :  13%|█▎        | 12781/100000 [3:35:42<14:11:18,  1.71it/s]
Train steps ... :  13%|█▎        | 12782/100000 [3:35:43<14:10:57,  1.71it/s]
Train steps ... :  13%|█▎        | 12783/100000 [3:35:43<14:11:31,  1.71it/s]
Train steps ... :  13%|█▎        | 12784/100000 [3:35:44<14:10:55,  1.71it/s]
Train steps ... :  13%|█▎        | 12785/100000 [3:35:44<14:11:54,  1.71it/s]
Train steps ... :  13%|█▎        | 12786/100000 [3:35:45<14:12:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12787/100000 [3:35:45<14:10:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12788/100000 [3:35:46<14:12:27,  1.71it/s]
Train steps ... :  13%|█▎        | 12789/100000 [3:35:47<14:12:41,  1.70it/s]
Train steps ... :  13%|█▎        | 12790/100000 [3:35:47<14:13:01,  1.70it/s]
Train steps ... :  13%|█▎        | 12791/100000 [3:35:48<14:11:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12792/100000 [3:35:48<14:12:56,  1.70it/s]
Train steps ... :  13%|█▎        | 12793/100000 [3:35:49<14:12:12,  1.71it/s]
Train steps ... :  13%|█▎        | 12794/100000 [3:35:50<14:11:25,  1.71it/s]
Train steps ... :  13%|█▎        | 12795/100000 [3:35:50<14:10:48,  1.71it/s]
Train steps ... :  13%|█▎        | 12796/100000 [3:35:51<14:10:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12797/100000 [3:35:51<14:10:58,  1.71it/s]
Train steps ... :  13%|█▎        | 12798/100000 [3:35:52<14:11:54,  1.71it/s]
Train steps ... :  13%|█▎        | 12799/100000 [3:35:53<14:10:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12800/100000 [3:35:53<14:09:40,  1.71it/s]Step... (12800 / 100000 | Loss: 0.9772289395332336, Learning Rate: 8.763819095477387e-05)
+
                                                                             
Step... (12800 / 100000 | Loss: 1.572427749633789, Learning Rate: 8.763819095477387e-05)
+
Train steps ... :  13%|█▎        | 12800/100000 [3:35:53<14:09:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12801/100000 [3:35:54<14:10:28,  1.71it/s]
Train steps ... :  13%|█▎        | 12802/100000 [3:35:54<14:10:07,  1.71it/s]
Train steps ... :  13%|█▎        | 12803/100000 [3:35:55<14:09:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12804/100000 [3:35:55<14:09:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12805/100000 [3:35:56<14:08:54,  1.71it/s]
Train steps ... :  13%|█▎        | 12806/100000 [3:35:57<14:08:33,  1.71it/s]
Train steps ... :  13%|█▎        | 12807/100000 [3:35:57<14:09:45,  1.71it/s]
Train steps ... :  13%|█▎        | 12808/100000 [3:35:58<14:09:23,  1.71it/s]
Train steps ... :  13%|█▎        | 12809/100000 [3:35:58<14:09:15,  1.71it/s]
Train steps ... :  13%|█▎        | 12810/100000 [3:35:59<14:09:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12811/100000 [3:36:00<14:11:58,  1.71it/s]
Train steps ... :  13%|█▎        | 12812/100000 [3:36:00<14:08:36,  1.71it/s]
Train steps ... :  13%|█▎        | 12813/100000 [3:36:01<14:09:34,  1.71it/s]
Train steps ... :  13%|█▎        | 12814/100000 [3:36:01<14:08:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12815/100000 [3:36:02<14:08:45,  1.71it/s]
Train steps ... :  13%|█▎        | 12816/100000 [3:36:02<14:09:39,  1.71it/s]
Train steps ... :  13%|█▎        | 12817/100000 [3:36:03<14:08:51,  1.71it/s]
Train steps ... :  13%|█▎        | 12818/100000 [3:36:04<14:09:27,  1.71it/s]
Train steps ... :  13%|█▎        | 12819/100000 [3:36:04<14:11:09,  1.71it/s]
Train steps ... :  13%|█▎        | 12820/100000 [3:36:05<14:11:22,  1.71it/s]
Train steps ... :  13%|█▎        | 12821/100000 [3:36:05<14:11:03,  1.71it/s]
Train steps ... :  13%|█▎        | 12822/100000 [3:36:06<14:10:48,  1.71it/s]
Train steps ... :  13%|█▎        | 12823/100000 [3:36:07<14:09:46,  1.71it/s]
Train steps ... :  13%|█▎        | 12824/100000 [3:36:07<14:09:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12825/100000 [3:36:08<14:10:42,  1.71it/s]Step... (12825 / 100000 | Loss: 1.165185809135437, Learning Rate: 8.761306532663317e-05)
+
                                                                             
Step... (12825 / 100000 | Loss: 0.9181386828422546, Learning Rate: 8.761306532663317e-05)
+
Train steps ... :  13%|█▎        | 12825/100000 [3:36:08<14:10:42,  1.71it/s]
Train steps ... :  13%|█▎        | 12826/100000 [3:36:08<14:10:48,  1.71it/s]
Train steps ... :  13%|█▎        | 12827/100000 [3:36:09<14:10:44,  1.71it/s]
Train steps ... :  13%|█▎        | 12828/100000 [3:36:09<14:10:55,  1.71it/s]
Train steps ... :  13%|█▎        | 12829/100000 [3:36:10<14:10:00,  1.71it/s]
Train steps ... :  13%|█▎        | 12830/100000 [3:36:11<14:10:52,  1.71it/s]
Train steps ... :  13%|█▎        | 12831/100000 [3:36:11<14:12:03,  1.71it/s]
Train steps ... :  13%|█▎        | 12832/100000 [3:36:12<14:12:30,  1.70it/s]
Train steps ... :  13%|█▎        | 12833/100000 [3:36:12<14:11:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12834/100000 [3:36:13<14:11:42,  1.71it/s]
Train steps ... :  13%|█▎        | 12835/100000 [3:36:14<14:13:55,  1.70it/s]
Train steps ... :  13%|█▎        | 12836/100000 [3:36:14<14:10:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12837/100000 [3:36:15<14:11:48,  1.71it/s]
Train steps ... :  13%|█▎        | 12838/100000 [3:36:15<14:10:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12839/100000 [3:36:16<14:12:02,  1.70it/s]
Train steps ... :  13%|█▎        | 12840/100000 [3:36:17<14:10:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12841/100000 [3:36:17<14:09:12,  1.71it/s]
Train steps ... :  13%|█▎        | 12842/100000 [3:36:18<14:09:07,  1.71it/s]
Train steps ... :  13%|█▎        | 12843/100000 [3:36:18<14:10:47,  1.71it/s]
Train steps ... :  13%|█▎        | 12844/100000 [3:36:19<14:11:19,  1.71it/s]
Train steps ... :  13%|█▎        | 12845/100000 [3:36:19<14:10:41,  1.71it/s]
Train steps ... :  13%|█▎        | 12846/100000 [3:36:20<14:11:36,  1.71it/s]
Train steps ... :  13%|█▎        | 12847/100000 [3:36:21<14:11:02,  1.71it/s]
Train steps ... :  13%|█▎        | 12848/100000 [3:36:21<14:11:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12849/100000 [3:36:22<14:10:11,  1.71it/s]
Train steps ... :  13%|█▎        | 12850/100000 [3:36:22<14:09:53,  1.71it/s]Step... (12850 / 100000 | Loss: 1.2508680820465088, Learning Rate: 8.758793969849247e-05)
+
                                                                             
Step... (12850 / 100000 | Loss: 1.7398700714111328, Learning Rate: 8.758793969849247e-05)
+
Train steps ... :  13%|█▎        | 12850/100000 [3:36:23<14:09:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12851/100000 [3:36:23<14:09:47,  1.71it/s]
Train steps ... :  13%|█▎        | 12852/100000 [3:36:24<14:10:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12853/100000 [3:36:24<14:09:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12854/100000 [3:36:25<14:13:04,  1.70it/s]
Train steps ... :  13%|█▎        | 12855/100000 [3:36:25<14:12:07,  1.70it/s]
Train steps ... :  13%|█▎        | 12856/100000 [3:36:26<14:11:12,  1.71it/s]
Train steps ... :  13%|█▎        | 12857/100000 [3:36:26<14:12:43,  1.70it/s]
Train steps ... :  13%|█▎        | 12858/100000 [3:36:27<14:11:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12859/100000 [3:36:28<14:12:59,  1.70it/s]
Train steps ... :  13%|█▎        | 12860/100000 [3:36:28<14:10:58,  1.71it/s]
Train steps ... :  13%|█▎        | 12861/100000 [3:36:29<14:09:36,  1.71it/s]
Train steps ... :  13%|█▎        | 12862/100000 [3:36:29<14:12:15,  1.70it/s]
Train steps ... :  13%|█▎        | 12863/100000 [3:36:30<14:11:02,  1.71it/s]
Train steps ... :  13%|█▎        | 12864/100000 [3:36:31<14:11:53,  1.70it/s]
Train steps ... :  13%|█▎        | 12865/100000 [3:36:31<14:11:50,  1.70it/s]
Train steps ... :  13%|█▎        | 12866/100000 [3:36:32<14:13:11,  1.70it/s]
Train steps ... :  13%|█▎        | 12867/100000 [3:36:32<14:10:55,  1.71it/s]
Train steps ... :  13%|█▎        | 12868/100000 [3:36:33<14:11:33,  1.71it/s]
Train steps ... :  13%|█▎        | 12869/100000 [3:36:34<14:12:36,  1.70it/s]
Train steps ... :  13%|█▎        | 12870/100000 [3:36:34<14:11:59,  1.70it/s]
Train steps ... :  13%|█▎        | 12871/100000 [3:36:35<14:10:03,  1.71it/s]
Train steps ... :  13%|█▎        | 12872/100000 [3:36:35<14:10:51,  1.71it/s]
Train steps ... :  13%|█▎        | 12873/100000 [3:36:36<14:09:58,  1.71it/s]
Train steps ... :  13%|█▎        | 12874/100000 [3:36:36<14:10:51,  1.71it/s]
Train steps ... :  13%|█▎        | 12875/100000 [3:36:37<14:09:42,  1.71it/s]Step... (12875 / 100000 | Loss: 1.4193646907806396, Learning Rate: 8.756281407035176e-05)
+
                                                                             
Step... (12875 / 100000 | Loss: 1.5369536876678467, Learning Rate: 8.756281407035176e-05)
+
Train steps ... :  13%|█▎        | 12875/100000 [3:36:37<14:09:42,  1.71it/s]
Train steps ... :  13%|█▎        | 12876/100000 [3:36:38<14:10:14,  1.71it/s]
Train steps ... :  13%|█▎        | 12877/100000 [3:36:38<14:10:08,  1.71it/s]
Train steps ... :  13%|█▎        | 12878/100000 [3:36:39<14:08:42,  1.71it/s]
Train steps ... :  13%|█▎        | 12879/100000 [3:36:39<14:09:11,  1.71it/s]
Train steps ... :  13%|█▎        | 12880/100000 [3:36:40<14:10:38,  1.71it/s]
Train steps ... :  13%|█▎        | 12881/100000 [3:36:41<14:08:38,  1.71it/s]
Train steps ... :  13%|█▎        | 12882/100000 [3:36:41<14:08:55,  1.71it/s]
Train steps ... :  13%|█▎        | 12883/100000 [3:36:42<14:08:32,  1.71it/s]
Train steps ... :  13%|█▎        | 12884/100000 [3:36:42<14:08:45,  1.71it/s]
Train steps ... :  13%|█▎        | 12885/100000 [3:36:43<14:08:28,  1.71it/s]
Train steps ... :  13%|█▎        | 12886/100000 [3:36:43<14:12:59,  1.70it/s]
Train steps ... :  13%|█▎        | 12887/100000 [3:36:44<14:14:42,  1.70it/s]
Train steps ... :  13%|█▎        | 12888/100000 [3:36:45<14:12:00,  1.70it/s]
Train steps ... :  13%|█▎        | 12889/100000 [3:36:45<14:15:33,  1.70it/s]
Train steps ... :  13%|█▎        | 12890/100000 [3:36:46<14:14:21,  1.70it/s]
Train steps ... :  13%|█▎        | 12891/100000 [3:36:46<14:14:11,  1.70it/s]
Train steps ... :  13%|█▎        | 12892/100000 [3:36:47<14:15:54,  1.70it/s]
Train steps ... :  13%|█▎        | 12893/100000 [3:36:48<14:11:48,  1.70it/s]
Train steps ... :  13%|█▎        | 12894/100000 [3:36:48<14:12:43,  1.70it/s]
Train steps ... :  13%|█▎        | 12895/100000 [3:36:49<14:13:50,  1.70it/s]
Train steps ... :  13%|█▎        | 12896/100000 [3:36:49<14:10:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12897/100000 [3:36:50<14:10:35,  1.71it/s]
Train steps ... :  13%|█▎        | 12898/100000 [3:36:51<14:09:44,  1.71it/s]
Train steps ... :  13%|█▎        | 12899/100000 [3:36:51<14:08:39,  1.71it/s]
Train steps ... :  13%|█▎        | 12900/100000 [3:36:52<14:08:23,  1.71it/s]Step... (12900 / 100000 | Loss: 1.276444911956787, Learning Rate: 8.753768844221106e-05)
+
                                                                             
Step... (12900 / 100000 | Loss: 1.6910758018493652, Learning Rate: 8.753768844221106e-05)
+
Train steps ... :  13%|█▎        | 12900/100000 [3:36:52<14:08:23,  1.71it/s]
Train steps ... :  13%|█▎        | 12901/100000 [3:36:52<14:08:33,  1.71it/s]
Train steps ... :  13%|█▎        | 12902/100000 [3:36:53<14:08:50,  1.71it/s]
Train steps ... :  13%|█▎        | 12903/100000 [3:36:53<14:11:55,  1.70it/s]
Train steps ... :  13%|█▎        | 12904/100000 [3:36:54<14:10:27,  1.71it/s]
Train steps ... :  13%|█▎        | 12905/100000 [3:36:55<14:10:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12906/100000 [3:36:55<14:09:28,  1.71it/s]
Train steps ... :  13%|█▎        | 12907/100000 [3:36:56<14:10:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12908/100000 [3:36:56<14:09:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12909/100000 [3:36:57<14:08:31,  1.71it/s]
Train steps ... :  13%|█▎        | 12910/100000 [3:36:58<14:08:32,  1.71it/s]
Train steps ... :  13%|█▎        | 12911/100000 [3:36:58<14:07:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12912/100000 [3:36:59<14:08:15,  1.71it/s]
Train steps ... :  13%|█▎        | 12913/100000 [3:36:59<14:08:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12914/100000 [3:37:00<14:08:34,  1.71it/s]
Train steps ... :  13%|█▎        | 12915/100000 [3:37:00<14:08:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12916/100000 [3:37:01<14:09:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12917/100000 [3:37:02<14:09:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12918/100000 [3:37:02<14:10:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12919/100000 [3:37:03<14:09:32,  1.71it/s]
Train steps ... :  13%|█▎        | 12920/100000 [3:37:03<14:09:52,  1.71it/s]
Train steps ... :  13%|█▎        | 12921/100000 [3:37:04<14:10:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12922/100000 [3:37:05<14:11:05,  1.71it/s]
Train steps ... :  13%|█▎        | 12923/100000 [3:37:05<14:10:13,  1.71it/s]
Train steps ... :  13%|█▎        | 12924/100000 [3:37:06<14:09:45,  1.71it/s]
Train steps ... :  13%|█▎        | 12925/100000 [3:37:06<14:11:08,  1.71it/s]Step... (12925 / 100000 | Loss: 0.6978647708892822, Learning Rate: 8.751256281407036e-05)
+
                                                                             
Step... (12925 / 100000 | Loss: 0.9010547995567322, Learning Rate: 8.751256281407036e-05)
+
Train steps ... :  13%|█▎        | 12925/100000 [3:37:07<14:11:08,  1.71it/s]
Train steps ... :  13%|█▎        | 12926/100000 [3:37:07<14:09:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12927/100000 [3:37:07<14:09:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12928/100000 [3:37:08<14:08:01,  1.71it/s]
Train steps ... :  13%|█▎        | 12929/100000 [3:37:09<14:07:51,  1.71it/s]
Train steps ... :  13%|█▎        | 12930/100000 [3:37:09<14:07:51,  1.71it/s]
Train steps ... :  13%|█▎        | 12931/100000 [3:37:10<14:10:27,  1.71it/s]
Train steps ... :  13%|█▎        | 12932/100000 [3:37:10<14:10:35,  1.71it/s]
Train steps ... :  13%|█▎        | 12933/100000 [3:37:11<14:09:51,  1.71it/s]
Train steps ... :  13%|█▎        | 12934/100000 [3:37:12<14:10:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12935/100000 [3:37:12<14:09:01,  1.71it/s]
Train steps ... :  13%|█▎        | 12936/100000 [3:37:13<14:08:34,  1.71it/s]
Train steps ... :  13%|█▎        | 12937/100000 [3:37:13<14:09:35,  1.71it/s]
Train steps ... :  13%|█▎        | 12938/100000 [3:37:14<14:09:07,  1.71it/s]
Train steps ... :  13%|█▎        | 12939/100000 [3:37:14<14:08:43,  1.71it/s]
Train steps ... :  13%|█▎        | 12940/100000 [3:37:15<14:09:00,  1.71it/s]
Train steps ... :  13%|█▎        | 12941/100000 [3:37:16<14:11:19,  1.70it/s]
Train steps ... :  13%|█▎        | 12942/100000 [3:37:16<14:11:07,  1.70it/s]
Train steps ... :  13%|█▎        | 12943/100000 [3:37:17<14:07:29,  1.71it/s]
Train steps ... :  13%|█▎        | 12944/100000 [3:37:17<14:07:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12945/100000 [3:37:18<14:10:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12946/100000 [3:37:19<14:09:23,  1.71it/s]
Train steps ... :  13%|█▎        | 12947/100000 [3:37:19<14:10:01,  1.71it/s]
Train steps ... :  13%|█▎        | 12948/100000 [3:37:20<14:10:17,  1.71it/s]
Train steps ... :  13%|█▎        | 12949/100000 [3:37:20<14:11:08,  1.70it/s]
Train steps ... :  13%|█▎        | 12950/100000 [3:37:21<14:10:15,  1.71it/s]Step... (12950 / 100000 | Loss: 0.9589788913726807, Learning Rate: 8.748743718592965e-05)
+
                                                                             
Step... (12950 / 100000 | Loss: 1.2753629684448242, Learning Rate: 8.748743718592965e-05)
+
Train steps ... :  13%|█▎        | 12950/100000 [3:37:21<14:10:15,  1.71it/s]
Train steps ... :  13%|█▎        | 12951/100000 [3:37:22<14:09:58,  1.71it/s]
Train steps ... :  13%|█▎        | 12952/100000 [3:37:22<14:09:31,  1.71it/s]
Train steps ... :  13%|█▎        | 12953/100000 [3:37:23<14:10:06,  1.71it/s]
Train steps ... :  13%|█▎        | 12954/100000 [3:37:23<14:11:22,  1.70it/s]
Train steps ... :  13%|█▎        | 12955/100000 [3:37:24<14:10:54,  1.70it/s]
Train steps ... :  13%|█▎        | 12956/100000 [3:37:24<14:11:36,  1.70it/s]
Train steps ... :  13%|█▎        | 12957/100000 [3:37:25<14:10:20,  1.71it/s]
Train steps ... :  13%|█▎        | 12958/100000 [3:37:26<14:12:18,  1.70it/s]
Train steps ... :  13%|█▎        | 12959/100000 [3:37:26<14:11:05,  1.70it/s]
Train steps ... :  13%|█▎        | 12960/100000 [3:37:27<14:12:26,  1.70it/s]
Train steps ... :  13%|█▎        | 12961/100000 [3:37:27<14:09:02,  1.71it/s]
Train steps ... :  13%|█▎        | 12962/100000 [3:37:28<14:08:35,  1.71it/s]
Train steps ... :  13%|█▎        | 12963/100000 [3:37:29<14:08:24,  1.71it/s]
Train steps ... :  13%|█▎        | 12964/100000 [3:37:29<14:08:00,  1.71it/s]
Train steps ... :  13%|█▎        | 12965/100000 [3:37:30<14:08:03,  1.71it/s]
Train steps ... :  13%|█▎        | 12966/100000 [3:37:30<14:09:16,  1.71it/s]
Train steps ... :  13%|█▎        | 12967/100000 [3:37:31<14:08:30,  1.71it/s]
Train steps ... :  13%|█▎        | 12968/100000 [3:37:31<14:08:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12969/100000 [3:37:32<14:08:35,  1.71it/s]
Train steps ... :  13%|█▎        | 12970/100000 [3:37:33<14:08:47,  1.71it/s]
Train steps ... :  13%|█▎        | 12971/100000 [3:37:33<14:09:52,  1.71it/s]
Train steps ... :  13%|█▎        | 12972/100000 [3:37:34<14:07:18,  1.71it/s]
Train steps ... :  13%|█▎        | 12973/100000 [3:37:34<14:08:50,  1.71it/s]
Train steps ... :  13%|█▎        | 12974/100000 [3:37:35<14:08:41,  1.71it/s]
Train steps ... :  13%|█▎        | 12975/100000 [3:37:36<14:10:10,  1.71it/s]Step... (12975 / 100000 | Loss: 1.2639601230621338, Learning Rate: 8.746231155778895e-05)
+
                                                                             
Step... (12975 / 100000 | Loss: 1.0709964036941528, Learning Rate: 8.746231155778895e-05)
+
Train steps ... :  13%|█▎        | 12975/100000 [3:37:36<14:10:10,  1.71it/s]
Train steps ... :  13%|█▎        | 12976/100000 [3:37:36<14:10:45,  1.70it/s]
Train steps ... :  13%|█▎        | 12977/100000 [3:37:37<14:09:01,  1.71it/s]
Train steps ... :  13%|█▎        | 12978/100000 [3:37:37<14:13:14,  1.70it/s]
Train steps ... :  13%|█▎        | 12979/100000 [3:37:38<14:09:44,  1.71it/s]
Train steps ... :  13%|█▎        | 12980/100000 [3:37:39<14:09:29,  1.71it/s]
Train steps ... :  13%|█▎        | 12981/100000 [3:37:39<14:09:21,  1.71it/s]
Train steps ... :  13%|█▎        | 12982/100000 [3:37:40<14:08:41,  1.71it/s]
Train steps ... :  13%|█▎        | 12983/100000 [3:37:40<14:07:59,  1.71it/s]
Train steps ... :  13%|█▎        | 12984/100000 [3:37:41<14:07:36,  1.71it/s]
Train steps ... :  13%|█▎        | 12985/100000 [3:37:41<14:07:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12986/100000 [3:37:42<14:08:40,  1.71it/s]
Train steps ... :  13%|█▎        | 12987/100000 [3:37:43<14:08:46,  1.71it/s]
Train steps ... :  13%|█▎        | 12988/100000 [3:37:43<14:08:55,  1.71it/s]
Train steps ... :  13%|█▎        | 12989/100000 [3:37:44<14:09:52,  1.71it/s]
Train steps ... :  13%|█▎        | 12990/100000 [3:37:44<14:11:03,  1.70it/s]
Train steps ... :  13%|█▎        | 12991/100000 [3:37:45<14:09:50,  1.71it/s]
Train steps ... :  13%|█▎        | 12992/100000 [3:37:46<14:08:25,  1.71it/s]
Train steps ... :  13%|█▎        | 12993/100000 [3:37:46<14:09:53,  1.71it/s]
Train steps ... :  13%|█▎        | 12994/100000 [3:37:47<14:09:01,  1.71it/s]
Train steps ... :  13%|█▎        | 12995/100000 [3:37:47<14:07:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12996/100000 [3:37:48<14:08:49,  1.71it/s]
Train steps ... :  13%|█▎        | 12997/100000 [3:37:48<14:09:12,  1.71it/s]
Train steps ... :  13%|█▎        | 12998/100000 [3:37:49<14:08:50,  1.71it/s]
Train steps ... :  13%|█▎        | 12999/100000 [3:37:50<14:09:33,  1.71it/s]
Train steps ... :  13%|█▎        | 13000/100000 [3:37:50<14:08:39,  1.71it/s]Step... (13000 / 100000 | Loss: 0.8067773580551147, Learning Rate: 8.743718592964825e-05)
+
                                                                             
Step... (13000 / 100000 | Loss: 1.246352195739746, Learning Rate: 8.743718592964825e-05)
+
Train steps ... :  13%|█▎        | 13000/100000 [3:37:51<14:08:39,  1.71it/s]
Train steps ... :  13%|█▎        | 13001/100000 [3:37:51<14:09:18,  1.71it/s]
Train steps ... :  13%|█▎        | 13002/100000 [3:37:51<14:08:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13003/100000 [3:37:52<14:09:19,  1.71it/s]
Train steps ... :  13%|█▎        | 13004/100000 [3:37:53<14:08:27,  1.71it/s]
Train steps ... :  13%|█▎        | 13005/100000 [3:37:53<14:08:01,  1.71it/s]
Train steps ... :  13%|█▎        | 13006/100000 [3:37:54<14:10:22,  1.71it/s]
Train steps ... :  13%|█▎        | 13007/100000 [3:37:54<14:08:04,  1.71it/s]
Train steps ... :  13%|█▎        | 13008/100000 [3:37:55<14:09:28,  1.71it/s]
Train steps ... :  13%|█▎        | 13009/100000 [3:37:55<14:08:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13010/100000 [3:37:56<14:07:43,  1.71it/s]
Train steps ... :  13%|█▎        | 13011/100000 [3:37:57<14:08:11,  1.71it/s]
Train steps ... :  13%|█▎        | 13012/100000 [3:37:57<14:08:38,  1.71it/s]
Train steps ... :  13%|█▎        | 13013/100000 [3:37:58<14:08:54,  1.71it/s]
Train steps ... :  13%|█▎        | 13014/100000 [3:37:58<14:10:03,  1.71it/s]
Train steps ... :  13%|█▎        | 13015/100000 [3:37:59<14:09:15,  1.71it/s]
Train steps ... :  13%|█▎        | 13016/100000 [3:38:00<14:09:10,  1.71it/s]
Train steps ... :  13%|█▎        | 13017/100000 [3:38:00<14:09:14,  1.71it/s]
Train steps ... :  13%|█▎        | 13018/100000 [3:38:01<14:09:30,  1.71it/s]
Train steps ... :  13%|█▎        | 13019/100000 [3:38:01<14:10:42,  1.70it/s]
Train steps ... :  13%|█▎        | 13020/100000 [3:38:02<14:11:14,  1.70it/s]
Train steps ... :  13%|█▎        | 13021/100000 [3:38:03<14:10:40,  1.70it/s]
Train steps ... :  13%|█▎        | 13022/100000 [3:38:03<14:08:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13023/100000 [3:38:04<14:08:19,  1.71it/s]
Train steps ... :  13%|█▎        | 13024/100000 [3:38:04<14:07:22,  1.71it/s]
Train steps ... :  13%|█▎        | 13025/100000 [3:38:05<14:06:56,  1.71it/s]Step... (13025 / 100000 | Loss: 1.05079984664917, Learning Rate: 8.741206030150753e-05)
+
                                                                             
Step... (13025 / 100000 | Loss: 1.0814599990844727, Learning Rate: 8.741206030150753e-05)
+
Train steps ... :  13%|█▎        | 13025/100000 [3:38:05<14:06:56,  1.71it/s]
Train steps ... :  13%|█▎        | 13026/100000 [3:38:05<14:07:19,  1.71it/s]
Train steps ... :  13%|█▎        | 13027/100000 [3:38:06<14:08:33,  1.71it/s]
Train steps ... :  13%|█▎        | 13028/100000 [3:38:07<14:07:43,  1.71it/s]
Train steps ... :  13%|█▎        | 13029/100000 [3:38:07<14:08:57,  1.71it/s]
Train steps ... :  13%|█▎        | 13030/100000 [3:38:08<14:09:23,  1.71it/s]
Train steps ... :  13%|█▎        | 13031/100000 [3:38:08<14:08:48,  1.71it/s]
Train steps ... :  13%|█▎        | 13032/100000 [3:38:09<14:08:16,  1.71it/s]
Train steps ... :  13%|█▎        | 13033/100000 [3:38:10<14:08:34,  1.71it/s]
Train steps ... :  13%|█▎        | 13034/100000 [3:38:10<14:09:00,  1.71it/s]
Train steps ... :  13%|█▎        | 13035/100000 [3:38:11<14:08:43,  1.71it/s]
Train steps ... :  13%|█▎        | 13036/100000 [3:38:11<14:09:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13037/100000 [3:38:12<14:09:18,  1.71it/s]
Train steps ... :  13%|█▎        | 13038/100000 [3:38:12<14:08:47,  1.71it/s]
Train steps ... :  13%|█▎        | 13039/100000 [3:38:13<14:09:24,  1.71it/s]
Train steps ... :  13%|█▎        | 13040/100000 [3:38:14<14:08:56,  1.71it/s]
Train steps ... :  13%|█▎        | 13041/100000 [3:38:14<14:08:35,  1.71it/s]
Train steps ... :  13%|█▎        | 13042/100000 [3:38:15<14:09:40,  1.71it/s]
Train steps ... :  13%|█▎        | 13043/100000 [3:38:15<14:08:41,  1.71it/s]
Train steps ... :  13%|█▎        | 13044/100000 [3:38:16<14:09:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13045/100000 [3:38:17<14:08:46,  1.71it/s]
Train steps ... :  13%|█▎        | 13046/100000 [3:38:17<14:07:53,  1.71it/s]
Train steps ... :  13%|█▎        | 13047/100000 [3:38:18<14:07:32,  1.71it/s]
Train steps ... :  13%|█▎        | 13048/100000 [3:38:18<14:07:20,  1.71it/s]
Train steps ... :  13%|█▎        | 13049/100000 [3:38:19<14:08:28,  1.71it/s]
Train steps ... :  13%|█▎        | 13050/100000 [3:38:20<14:08:51,  1.71it/s]Step... (13050 / 100000 | Loss: 1.0481114387512207, Learning Rate: 8.738693467336684e-05)
+
                                                                             
Step... (13050 / 100000 | Loss: 1.143976092338562, Learning Rate: 8.738693467336684e-05)
+
Train steps ... :  13%|█▎        | 13050/100000 [3:38:20<14:08:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13051/100000 [3:38:20<14:08:47,  1.71it/s]
Train steps ... :  13%|█▎        | 13052/100000 [3:38:21<14:07:39,  1.71it/s]
Train steps ... :  13%|█▎        | 13053/100000 [3:38:21<14:07:57,  1.71it/s]
Train steps ... :  13%|█▎        | 13054/100000 [3:38:22<14:06:53,  1.71it/s]
Train steps ... :  13%|█▎        | 13055/100000 [3:38:22<14:07:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13056/100000 [3:38:23<14:07:41,  1.71it/s]
Train steps ... :  13%|█▎        | 13057/100000 [3:38:24<14:08:55,  1.71it/s]
Train steps ... :  13%|█▎        | 13058/100000 [3:38:24<14:07:55,  1.71it/s]
Train steps ... :  13%|█▎        | 13059/100000 [3:38:25<14:09:45,  1.71it/s]
Train steps ... :  13%|█▎        | 13060/100000 [3:38:25<14:10:10,  1.70it/s]
Train steps ... :  13%|█▎        | 13061/100000 [3:38:26<14:09:43,  1.71it/s]
Train steps ... :  13%|█▎        | 13062/100000 [3:38:27<14:10:39,  1.70it/s]
Train steps ... :  13%|█▎        | 13063/100000 [3:38:27<14:09:46,  1.71it/s]
Train steps ... :  13%|█▎        | 13064/100000 [3:38:28<14:10:04,  1.70it/s]
Train steps ... :  13%|█▎        | 13065/100000 [3:38:28<14:09:25,  1.71it/s]
Train steps ... :  13%|█▎        | 13066/100000 [3:38:29<14:13:46,  1.70it/s]
Train steps ... :  13%|█▎        | 13067/100000 [3:38:29<14:11:45,  1.70it/s]
Train steps ... :  13%|█▎        | 13068/100000 [3:38:30<14:09:46,  1.70it/s]
Train steps ... :  13%|█▎        | 13069/100000 [3:38:31<14:10:45,  1.70it/s]
Train steps ... :  13%|█▎        | 13070/100000 [3:38:31<14:09:55,  1.70it/s]
Train steps ... :  13%|█▎        | 13071/100000 [3:38:32<14:08:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13072/100000 [3:38:32<14:09:41,  1.71it/s]
Train steps ... :  13%|█▎        | 13073/100000 [3:38:33<14:08:57,  1.71it/s]
Train steps ... :  13%|█▎        | 13074/100000 [3:38:34<14:11:55,  1.70it/s]
Train steps ... :  13%|█▎        | 13075/100000 [3:38:34<14:08:21,  1.71it/s]Step... (13075 / 100000 | Loss: 0.893976092338562, Learning Rate: 8.736180904522614e-05)
+
                                                                             
Step... (13075 / 100000 | Loss: 1.4221524000167847, Learning Rate: 8.736180904522614e-05)
+
Train steps ... :  13%|█▎        | 13075/100000 [3:38:34<14:08:21,  1.71it/s]
Train steps ... :  13%|█▎        | 13076/100000 [3:38:35<14:08:19,  1.71it/s]
Train steps ... :  13%|█▎        | 13077/100000 [3:38:35<14:08:50,  1.71it/s]
Train steps ... :  13%|█▎        | 13078/100000 [3:38:36<14:07:23,  1.71it/s]
Train steps ... :  13%|█▎        | 13079/100000 [3:38:37<14:07:53,  1.71it/s]
Train steps ... :  13%|█▎        | 13080/100000 [3:38:37<14:08:28,  1.71it/s]
Train steps ... :  13%|█▎        | 13081/100000 [3:38:38<14:09:09,  1.71it/s]
Train steps ... :  13%|█▎        | 13082/100000 [3:38:38<14:10:10,  1.70it/s]
Train steps ... :  13%|█▎        | 13083/100000 [3:38:39<14:08:43,  1.71it/s]
Train steps ... :  13%|█▎        | 13084/100000 [3:38:39<14:07:03,  1.71it/s]
Train steps ... :  13%|█▎        | 13085/100000 [3:38:40<14:08:13,  1.71it/s]
Train steps ... :  13%|█▎        | 13086/100000 [3:38:41<14:06:16,  1.71it/s]
Train steps ... :  13%|█▎        | 13087/100000 [3:38:41<14:07:48,  1.71it/s]
Train steps ... :  13%|█▎        | 13088/100000 [3:38:42<14:07:43,  1.71it/s]
Train steps ... :  13%|█▎        | 13089/100000 [3:38:42<14:08:50,  1.71it/s]
Train steps ... :  13%|█▎        | 13090/100000 [3:38:43<14:07:13,  1.71it/s]
Train steps ... :  13%|█▎        | 13091/100000 [3:38:44<14:09:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13092/100000 [3:38:44<14:08:02,  1.71it/s]
Train steps ... :  13%|█▎        | 13093/100000 [3:38:45<14:08:12,  1.71it/s]
Train steps ... :  13%|█▎        | 13094/100000 [3:38:45<14:07:55,  1.71it/s]
Train steps ... :  13%|█▎        | 13095/100000 [3:38:46<14:07:22,  1.71it/s]
Train steps ... :  13%|█▎        | 13096/100000 [3:38:46<14:08:41,  1.71it/s]
Train steps ... :  13%|█▎        | 13097/100000 [3:38:47<14:09:32,  1.70it/s]
Train steps ... :  13%|█▎        | 13098/100000 [3:38:48<14:07:58,  1.71it/s]
Train steps ... :  13%|█▎        | 13099/100000 [3:38:48<14:09:12,  1.71it/s]
Train steps ... :  13%|█▎        | 13100/100000 [3:38:49<14:09:13,  1.71it/s]Step... (13100 / 100000 | Loss: 1.0353952646255493, Learning Rate: 8.733668341708543e-05)
+
                                                                             
Step... (13100 / 100000 | Loss: 1.5076520442962646, Learning Rate: 8.733668341708543e-05)
+
Train steps ... :  13%|█▎        | 13100/100000 [3:38:49<14:09:13,  1.71it/s]
Train steps ... :  13%|█▎        | 13101/100000 [3:38:49<14:09:01,  1.71it/s]
Train steps ... :  13%|█▎        | 13102/100000 [3:38:50<14:08:22,  1.71it/s]
Train steps ... :  13%|█▎        | 13103/100000 [3:38:51<14:08:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13104/100000 [3:38:51<14:08:59,  1.71it/s]
Train steps ... :  13%|█▎        | 13105/100000 [3:38:52<14:09:33,  1.70it/s]
Train steps ... :  13%|█▎        | 13106/100000 [3:38:52<14:07:45,  1.71it/s]
Train steps ... :  13%|█▎        | 13107/100000 [3:38:53<14:07:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13108/100000 [3:38:53<14:07:41,  1.71it/s]
Train steps ... :  13%|█▎        | 13109/100000 [3:38:54<14:08:26,  1.71it/s]
Train steps ... :  13%|█▎        | 13110/100000 [3:38:55<14:08:26,  1.71it/s]
Train steps ... :  13%|█▎        | 13111/100000 [3:38:55<14:07:18,  1.71it/s]
Train steps ... :  13%|█▎        | 13112/100000 [3:38:56<14:07:14,  1.71it/s]
Train steps ... :  13%|█▎        | 13113/100000 [3:38:56<14:07:33,  1.71it/s]
Train steps ... :  13%|█▎        | 13114/100000 [3:38:57<14:06:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13115/100000 [3:38:58<14:06:52,  1.71it/s]
Train steps ... :  13%|█▎        | 13116/100000 [3:38:58<14:08:13,  1.71it/s]
Train steps ... :  13%|█▎        | 13117/100000 [3:38:59<14:06:21,  1.71it/s]
Train steps ... :  13%|█▎        | 13118/100000 [3:38:59<14:09:35,  1.70it/s]
Train steps ... :  13%|█▎        | 13119/100000 [3:39:00<14:07:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13120/100000 [3:39:01<14:08:25,  1.71it/s]
Train steps ... :  13%|█▎        | 13121/100000 [3:39:01<14:08:31,  1.71it/s]
Train steps ... :  13%|█▎        | 13122/100000 [3:39:02<14:07:56,  1.71it/s]
Train steps ... :  13%|█▎        | 13123/100000 [3:39:02<14:07:54,  1.71it/s]
Train steps ... :  13%|█▎        | 13124/100000 [3:39:03<14:09:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13125/100000 [3:39:03<14:09:31,  1.70it/s]Step... (13125 / 100000 | Loss: 0.8317340612411499, Learning Rate: 8.731155778894473e-05)
+
                                                                             
Step... (13125 / 100000 | Loss: 1.1826554536819458, Learning Rate: 8.731155778894473e-05)
+
Train steps ... :  13%|█▎        | 13125/100000 [3:39:04<14:09:31,  1.70it/s]
Train steps ... :  13%|█▎        | 13126/100000 [3:39:04<14:10:02,  1.70it/s]
Train steps ... :  13%|█▎        | 13127/100000 [3:39:05<14:09:07,  1.71it/s]
Train steps ... :  13%|█▎        | 13128/100000 [3:39:05<14:08:23,  1.71it/s]
Train steps ... :  13%|█▎        | 13129/100000 [3:39:06<14:08:48,  1.71it/s]
Train steps ... :  13%|█▎        | 13130/100000 [3:39:06<14:07:48,  1.71it/s]
Train steps ... :  13%|█▎        | 13131/100000 [3:39:07<14:07:57,  1.71it/s]
Train steps ... :  13%|█▎        | 13132/100000 [3:39:08<14:11:04,  1.70it/s]
Train steps ... :  13%|█▎        | 13133/100000 [3:39:08<14:07:09,  1.71it/s]
Train steps ... :  13%|█▎        | 13134/100000 [3:39:09<14:07:27,  1.71it/s]
Train steps ... :  13%|█▎        | 13135/100000 [3:39:09<14:07:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13136/100000 [3:39:10<14:06:45,  1.71it/s]
Train steps ... :  13%|█▎        | 13137/100000 [3:39:10<14:06:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13138/100000 [3:39:11<14:06:31,  1.71it/s]
Train steps ... :  13%|█▎        | 13139/100000 [3:39:12<14:07:30,  1.71it/s]
Train steps ... :  13%|█▎        | 13140/100000 [3:39:12<14:08:04,  1.71it/s]
Train steps ... :  13%|█▎        | 13141/100000 [3:39:13<14:08:38,  1.71it/s]
Train steps ... :  13%|█▎        | 13142/100000 [3:39:13<14:07:19,  1.71it/s]
Train steps ... :  13%|█▎        | 13143/100000 [3:39:14<14:07:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13144/100000 [3:39:15<14:10:15,  1.70it/s]
Train steps ... :  13%|█▎        | 13145/100000 [3:39:15<14:09:30,  1.70it/s]
Train steps ... :  13%|█▎        | 13146/100000 [3:39:16<14:09:07,  1.70it/s]
Train steps ... :  13%|█▎        | 13147/100000 [3:39:16<14:09:39,  1.70it/s]
Train steps ... :  13%|█▎        | 13148/100000 [3:39:17<14:11:16,  1.70it/s]
Train steps ... :  13%|█▎        | 13149/100000 [3:39:18<14:07:48,  1.71it/s]
Train steps ... :  13%|█▎        | 13150/100000 [3:39:18<14:07:04,  1.71it/s]Step... (13150 / 100000 | Loss: 0.9299571514129639, Learning Rate: 8.728643216080403e-05)
+
                                                                             
Step... (13150 / 100000 | Loss: 1.5200905799865723, Learning Rate: 8.728643216080403e-05)
+
Train steps ... :  13%|█▎        | 13150/100000 [3:39:18<14:07:04,  1.71it/s]
Train steps ... :  13%|█▎        | 13151/100000 [3:39:19<14:08:13,  1.71it/s]
Train steps ... :  13%|█▎        | 13152/100000 [3:39:19<14:06:45,  1.71it/s]
Train steps ... :  13%|█▎        | 13153/100000 [3:39:20<14:06:56,  1.71it/s]
Train steps ... :  13%|█▎        | 13154/100000 [3:39:20<14:08:32,  1.71it/s]
Train steps ... :  13%|█▎        | 13155/100000 [3:39:21<14:09:53,  1.70it/s]
Train steps ... :  13%|█▎        | 13156/100000 [3:39:22<14:07:20,  1.71it/s]
Train steps ... :  13%|█▎        | 13157/100000 [3:39:22<14:08:11,  1.71it/s]
Train steps ... :  13%|█▎        | 13158/100000 [3:39:23<14:07:35,  1.71it/s]
Train steps ... :  13%|█▎        | 13159/100000 [3:39:23<14:06:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13160/100000 [3:39:24<14:09:14,  1.70it/s]
Train steps ... :  13%|█▎        | 13161/100000 [3:39:25<14:09:12,  1.70it/s]
Train steps ... :  13%|█▎        | 13162/100000 [3:39:25<14:09:21,  1.70it/s]
Train steps ... :  13%|█▎        | 13163/100000 [3:39:26<14:09:59,  1.70it/s]
Train steps ... :  13%|█▎        | 13164/100000 [3:39:26<14:10:32,  1.70it/s]
Train steps ... :  13%|█▎        | 13165/100000 [3:39:27<14:08:34,  1.71it/s]
Train steps ... :  13%|█▎        | 13166/100000 [3:39:27<14:07:30,  1.71it/s]
Train steps ... :  13%|█▎        | 13167/100000 [3:39:28<14:07:38,  1.71it/s]
Train steps ... :  13%|█▎        | 13168/100000 [3:39:29<14:07:41,  1.71it/s]
Train steps ... :  13%|█▎        | 13169/100000 [3:39:29<14:07:27,  1.71it/s]
Train steps ... :  13%|█▎        | 13170/100000 [3:39:30<14:08:24,  1.71it/s]
Train steps ... :  13%|█▎        | 13171/100000 [3:39:30<14:09:02,  1.70it/s]
Train steps ... :  13%|█▎        | 13172/100000 [3:39:31<14:07:58,  1.71it/s]
Train steps ... :  13%|█▎        | 13173/100000 [3:39:32<14:07:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13174/100000 [3:39:32<14:08:16,  1.71it/s]
Train steps ... :  13%|█▎        | 13175/100000 [3:39:33<14:08:08,  1.71it/s]Step... (13175 / 100000 | Loss: 1.289370059967041, Learning Rate: 8.726130653266332e-05)
+
                                                                             
Step... (13175 / 100000 | Loss: 1.255817174911499, Learning Rate: 8.726130653266332e-05)
+
Train steps ... :  13%|█▎        | 13175/100000 [3:39:33<14:08:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13176/100000 [3:39:33<14:07:09,  1.71it/s]
Train steps ... :  13%|█▎        | 13177/100000 [3:39:34<14:07:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13178/100000 [3:39:35<14:07:06,  1.71it/s]
Train steps ... :  13%|█▎        | 13179/100000 [3:39:35<14:09:56,  1.70it/s]
Train steps ... :  13%|█▎        | 13180/100000 [3:39:36<14:10:02,  1.70it/s]
Train steps ... :  13%|█▎        | 13181/100000 [3:39:36<14:08:42,  1.70it/s]
Train steps ... :  13%|█▎        | 13182/100000 [3:39:37<14:08:14,  1.71it/s]
Train steps ... :  13%|█▎        | 13183/100000 [3:39:37<14:09:47,  1.70it/s]
Train steps ... :  13%|█▎        | 13184/100000 [3:39:38<14:09:52,  1.70it/s]
Train steps ... :  13%|█▎        | 13185/100000 [3:39:39<14:06:57,  1.71it/s]
Train steps ... :  13%|█▎        | 13186/100000 [3:39:39<14:06:12,  1.71it/s]
Train steps ... :  13%|█▎        | 13187/100000 [3:39:40<14:06:29,  1.71it/s]
Train steps ... :  13%|█▎        | 13188/100000 [3:39:40<14:05:31,  1.71it/s]
Train steps ... :  13%|█▎        | 13189/100000 [3:39:41<14:05:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13190/100000 [3:39:42<14:08:12,  1.71it/s]
Train steps ... :  13%|█▎        | 13191/100000 [3:39:42<14:05:02,  1.71it/s]
Train steps ... :  13%|█▎        | 13192/100000 [3:39:43<14:06:16,  1.71it/s]
Train steps ... :  13%|█▎        | 13193/100000 [3:39:43<14:06:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13194/100000 [3:39:44<14:06:40,  1.71it/s]
Train steps ... :  13%|█▎        | 13195/100000 [3:39:44<14:07:29,  1.71it/s]
Train steps ... :  13%|█▎        | 13196/100000 [3:39:45<14:05:56,  1.71it/s]
Train steps ... :  13%|█▎        | 13197/100000 [3:39:46<14:06:58,  1.71it/s]
Train steps ... :  13%|█▎        | 13198/100000 [3:39:46<14:06:49,  1.71it/s]
Train steps ... :  13%|█▎        | 13199/100000 [3:39:47<14:06:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13200/100000 [3:39:47<14:05:55,  1.71it/s]Step... (13200 / 100000 | Loss: 0.9631471037864685, Learning Rate: 8.723618090452261e-05)
+
                                                                             
Step... (13200 / 100000 | Loss: 1.3956916332244873, Learning Rate: 8.723618090452261e-05)
+
Train steps ... :  13%|█▎        | 13200/100000 [3:39:48<14:05:55,  1.71it/s]
Train steps ... :  13%|█▎        | 13201/100000 [3:39:48<14:08:30,  1.70it/s]
Train steps ... :  13%|█▎        | 13202/100000 [3:39:49<14:06:28,  1.71it/s]
Train steps ... :  13%|█▎        | 13203/100000 [3:39:49<14:06:03,  1.71it/s]
Train steps ... :  13%|█▎        | 13204/100000 [3:39:50<14:05:43,  1.71it/s]
Train steps ... :  13%|█▎        | 13205/100000 [3:39:50<14:05:04,  1.71it/s]
Train steps ... :  13%|█▎        | 13206/100000 [3:39:51<14:06:24,  1.71it/s]
Train steps ... :  13%|█▎        | 13207/100000 [3:39:51<14:06:50,  1.71it/s]
Train steps ... :  13%|█▎        | 13208/100000 [3:39:52<14:06:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13209/100000 [3:39:53<14:08:58,  1.70it/s]
Train steps ... :  13%|█▎        | 13210/100000 [3:39:53<14:06:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13211/100000 [3:39:54<14:06:04,  1.71it/s]
Train steps ... :  13%|█▎        | 13212/100000 [3:39:54<14:06:03,  1.71it/s]
Train steps ... :  13%|█▎        | 13213/100000 [3:39:55<14:05:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13214/100000 [3:39:56<14:08:11,  1.71it/s]
Train steps ... :  13%|█▎        | 13215/100000 [3:39:56<14:07:11,  1.71it/s]
Train steps ... :  13%|█▎        | 13216/100000 [3:39:57<14:06:29,  1.71it/s]
Train steps ... :  13%|█▎        | 13217/100000 [3:39:57<14:06:09,  1.71it/s]
Train steps ... :  13%|█▎        | 13218/100000 [3:39:58<14:07:09,  1.71it/s]
Train steps ... :  13%|█▎        | 13219/100000 [3:39:59<14:09:23,  1.70it/s]
Train steps ... :  13%|█▎        | 13220/100000 [3:39:59<14:06:46,  1.71it/s]
Train steps ... :  13%|█▎        | 13221/100000 [3:40:00<14:06:33,  1.71it/s]
Train steps ... :  13%|█▎        | 13222/100000 [3:40:00<14:06:18,  1.71it/s]
Train steps ... :  13%|█▎        | 13223/100000 [3:40:01<14:05:40,  1.71it/s]
Train steps ... :  13%|█▎        | 13224/100000 [3:40:01<14:05:38,  1.71it/s]
Train steps ... :  13%|█▎        | 13225/100000 [3:40:02<14:07:03,  1.71it/s]Step... (13225 / 100000 | Loss: 1.0586438179016113, Learning Rate: 8.721105527638192e-05)
+
                                                                             
Step... (13225 / 100000 | Loss: 0.6645438075065613, Learning Rate: 8.721105527638192e-05)
+
Train steps ... :  13%|█▎        | 13225/100000 [3:40:02<14:07:03,  1.71it/s]
Train steps ... :  13%|█▎        | 13226/100000 [3:40:03<14:06:58,  1.71it/s]
Train steps ... :  13%|█▎        | 13227/100000 [3:40:03<14:06:14,  1.71it/s]
Train steps ... :  13%|█▎        | 13228/100000 [3:40:04<14:05:28,  1.71it/s]
Train steps ... :  13%|█▎        | 13229/100000 [3:40:04<14:08:38,  1.70it/s]
Train steps ... :  13%|█▎        | 13230/100000 [3:40:05<14:05:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13231/100000 [3:40:06<14:05:16,  1.71it/s]
Train steps ... :  13%|█▎        | 13232/100000 [3:40:06<14:06:53,  1.71it/s]
Train steps ... :  13%|█▎        | 13233/100000 [3:40:07<14:05:20,  1.71it/s]
Train steps ... :  13%|█▎        | 13234/100000 [3:40:07<14:05:13,  1.71it/s]
Train steps ... :  13%|█▎        | 13235/100000 [3:40:08<14:05:48,  1.71it/s]
Train steps ... :  13%|█▎        | 13236/100000 [3:40:08<14:07:18,  1.71it/s]
Train steps ... :  13%|█▎        | 13237/100000 [3:40:09<14:06:29,  1.71it/s]
Train steps ... :  13%|█▎        | 13238/100000 [3:40:10<14:06:15,  1.71it/s]
Train steps ... :  13%|█▎        | 13239/100000 [3:40:10<14:06:22,  1.71it/s]
Train steps ... :  13%|█▎        | 13240/100000 [3:40:11<14:06:55,  1.71it/s]
Train steps ... :  13%|█▎        | 13241/100000 [3:40:11<14:05:21,  1.71it/s]
Train steps ... :  13%|█▎        | 13242/100000 [3:40:12<14:08:09,  1.70it/s]
Train steps ... :  13%|█▎        | 13243/100000 [3:40:13<14:06:49,  1.71it/s]
Train steps ... :  13%|█▎        | 13244/100000 [3:40:13<14:05:50,  1.71it/s]
Train steps ... :  13%|█▎        | 13245/100000 [3:40:14<14:06:12,  1.71it/s]
Train steps ... :  13%|█▎        | 13246/100000 [3:40:14<14:07:48,  1.71it/s]
Train steps ... :  13%|█▎        | 13247/100000 [3:40:15<14:04:13,  1.71it/s]
Train steps ... :  13%|█▎        | 13248/100000 [3:40:15<14:04:43,  1.71it/s]
Train steps ... :  13%|█▎        | 13249/100000 [3:40:16<14:05:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13250/100000 [3:40:17<14:08:38,  1.70it/s]Step... (13250 / 100000 | Loss: 1.2646697759628296, Learning Rate: 8.71859296482412e-05)
+
                                                                             
Step... (13250 / 100000 | Loss: 1.2003215551376343, Learning Rate: 8.71859296482412e-05)
+
Train steps ... :  13%|█▎        | 13250/100000 [3:40:17<14:08:38,  1.70it/s]
Train steps ... :  13%|█▎        | 13251/100000 [3:40:17<14:06:23,  1.71it/s]
Train steps ... :  13%|█▎        | 13252/100000 [3:40:18<14:06:20,  1.71it/s]
Train steps ... :  13%|█▎        | 13253/100000 [3:40:18<14:08:53,  1.70it/s]
Train steps ... :  13%|█▎        | 13254/100000 [3:40:19<14:04:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13255/100000 [3:40:20<14:05:03,  1.71it/s]
Train steps ... :  13%|█▎        | 13256/100000 [3:40:20<14:09:19,  1.70it/s]
Train steps ... :  13%|█▎        | 13257/100000 [3:40:21<14:06:17,  1.71it/s]
Train steps ... :  13%|█▎        | 13258/100000 [3:40:21<14:08:03,  1.70it/s]
Train steps ... :  13%|█▎        | 13259/100000 [3:40:22<14:05:56,  1.71it/s]
Train steps ... :  13%|█▎        | 13260/100000 [3:40:23<14:07:15,  1.71it/s]
Train steps ... :  13%|█▎        | 13261/100000 [3:40:23<14:06:07,  1.71it/s]
Train steps ... :  13%|█▎        | 13262/100000 [3:40:24<14:08:11,  1.70it/s]
Train steps ... :  13%|█▎        | 13263/100000 [3:40:24<14:07:37,  1.71it/s]
Train steps ... :  13%|█▎        | 13264/100000 [3:40:25<14:07:26,  1.71it/s]
Train steps ... :  13%|█▎        | 13265/100000 [3:40:25<14:08:40,  1.70it/s]
Train steps ... :  13%|█▎        | 13266/100000 [3:40:26<14:10:00,  1.70it/s]
Train steps ... :  13%|█▎        | 13267/100000 [3:40:27<14:11:27,  1.70it/s]
Train steps ... :  13%|█▎        | 13268/100000 [3:40:27<14:09:55,  1.70it/s]
Train steps ... :  13%|█▎        | 13269/100000 [3:40:28<14:11:37,  1.70it/s]
Train steps ... :  13%|█▎        | 13270/100000 [3:40:28<14:11:53,  1.70it/s]
Train steps ... :  13%|█▎        | 13271/100000 [3:40:29<14:08:24,  1.70it/s]
Train steps ... :  13%|█▎        | 13272/100000 [3:40:30<14:09:22,  1.70it/s]
Train steps ... :  13%|█▎        | 13273/100000 [3:40:30<14:12:26,  1.70it/s]
Train steps ... :  13%|█▎        | 13274/100000 [3:40:31<14:10:50,  1.70it/s]
Train steps ... :  13%|█▎        | 13275/100000 [3:40:31<14:09:40,  1.70it/s]Step... (13275 / 100000 | Loss: 0.9778704643249512, Learning Rate: 8.716080402010051e-05)
+
                                                                             
Step... (13275 / 100000 | Loss: 0.8278745412826538, Learning Rate: 8.716080402010051e-05)
+
Train steps ... :  13%|█▎        | 13275/100000 [3:40:32<14:09:40,  1.70it/s]
Train steps ... :  13%|█▎        | 13276/100000 [3:40:32<14:08:06,  1.70it/s]
Train steps ... :  13%|█▎        | 13277/100000 [3:40:33<14:08:41,  1.70it/s]
Train steps ... :  13%|█▎        | 13278/100000 [3:40:33<14:09:58,  1.70it/s]
Train steps ... :  13%|█▎        | 13279/100000 [3:40:34<14:07:58,  1.70it/s]
Train steps ... :  13%|█▎        | 13280/100000 [3:40:34<14:09:36,  1.70it/s]
Train steps ... :  13%|█▎        | 13281/100000 [3:40:35<14:06:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13282/100000 [3:40:35<14:07:18,  1.71it/s]
Train steps ... :  13%|█▎        | 13283/100000 [3:40:36<14:05:53,  1.71it/s]
Train steps ... :  13%|█▎        | 13284/100000 [3:40:37<14:09:38,  1.70it/s]
Train steps ... :  13%|█▎        | 13285/100000 [3:40:37<14:05:13,  1.71it/s]
Train steps ... :  13%|█▎        | 13286/100000 [3:40:38<14:05:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13287/100000 [3:40:38<14:07:58,  1.70it/s]
Train steps ... :  13%|█▎        | 13288/100000 [3:40:39<14:07:40,  1.70it/s]
Train steps ... :  13%|█▎        | 13289/100000 [3:40:40<14:06:09,  1.71it/s]
Train steps ... :  13%|█▎        | 13290/100000 [3:40:40<14:05:54,  1.71it/s]
Train steps ... :  13%|█▎        | 13291/100000 [3:40:41<14:05:50,  1.71it/s]
Train steps ... :  13%|█▎        | 13292/100000 [3:40:41<14:05:33,  1.71it/s]
Train steps ... :  13%|█▎        | 13293/100000 [3:40:42<14:04:26,  1.71it/s]
Train steps ... :  13%|█▎        | 13294/100000 [3:40:42<14:04:04,  1.71it/s]
Train steps ... :  13%|█▎        | 13295/100000 [3:40:43<14:06:49,  1.71it/s]
Train steps ... :  13%|█▎        | 13296/100000 [3:40:44<14:04:34,  1.71it/s]
Train steps ... :  13%|█▎        | 13297/100000 [3:40:44<14:06:23,  1.71it/s]
Train steps ... :  13%|█▎        | 13298/100000 [3:40:45<14:08:39,  1.70it/s]
Train steps ... :  13%|█▎        | 13299/100000 [3:40:45<14:08:16,  1.70it/s]
Train steps ... :  13%|█▎        | 13300/100000 [3:40:46<14:05:04,  1.71it/s]Step... (13300 / 100000 | Loss: 1.5474879741668701, Learning Rate: 8.713567839195981e-05)
+
                                                                             
Step... (13300 / 100000 | Loss: 1.063873052597046, Learning Rate: 8.713567839195981e-05)
+
Train steps ... :  13%|█▎        | 13300/100000 [3:40:46<14:05:04,  1.71it/s]
Train steps ... :  13%|█▎        | 13301/100000 [3:40:47<14:05:28,  1.71it/s]
Train steps ... :  13%|█▎        | 13302/100000 [3:40:47<14:05:27,  1.71it/s]
Train steps ... :  13%|█▎        | 13303/100000 [3:40:48<14:07:21,  1.71it/s]
Train steps ... :  13%|█▎        | 13304/100000 [3:40:48<14:06:13,  1.71it/s]
Train steps ... :  13%|█▎        | 13305/100000 [3:40:49<14:07:29,  1.70it/s]
Train steps ... :  13%|█▎        | 13306/100000 [3:40:49<14:06:38,  1.71it/s]
Train steps ... :  13%|█▎        | 13307/100000 [3:40:50<14:09:23,  1.70it/s]
Train steps ... :  13%|█▎        | 13308/100000 [3:40:51<14:08:50,  1.70it/s]
Train steps ... :  13%|█▎        | 13309/100000 [3:40:51<14:07:19,  1.71it/s]
Train steps ... :  13%|█▎        | 13310/100000 [3:40:52<14:07:56,  1.70it/s]
Train steps ... :  13%|█▎        | 13311/100000 [3:40:52<14:08:20,  1.70it/s]
Train steps ... :  13%|█▎        | 13312/100000 [3:40:53<14:07:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13313/100000 [3:40:54<14:08:29,  1.70it/s]
Train steps ... :  13%|█▎        | 13314/100000 [3:40:54<14:07:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13315/100000 [3:40:55<14:06:53,  1.71it/s]
Train steps ... :  13%|█▎        | 13316/100000 [3:40:55<14:06:54,  1.71it/s]
Train steps ... :  13%|█▎        | 13317/100000 [3:40:56<14:05:46,  1.71it/s]
Train steps ... :  13%|█▎        | 13318/100000 [3:40:57<14:05:10,  1.71it/s]
Train steps ... :  13%|█▎        | 13319/100000 [3:40:57<14:06:33,  1.71it/s]
Train steps ... :  13%|█▎        | 13320/100000 [3:40:58<14:06:26,  1.71it/s]
Train steps ... :  13%|█▎        | 13321/100000 [3:40:58<14:05:24,  1.71it/s]
Train steps ... :  13%|█▎        | 13322/100000 [3:40:59<14:05:32,  1.71it/s]
Train steps ... :  13%|█▎        | 13323/100000 [3:40:59<14:04:56,  1.71it/s]
Train steps ... :  13%|█▎        | 13324/100000 [3:41:00<14:04:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13325/100000 [3:41:01<14:04:57,  1.71it/s]Step... (13325 / 100000 | Loss: 1.2979741096496582, Learning Rate: 8.71105527638191e-05)
+
                                                                             
Step... (13325 / 100000 | Loss: 1.1040046215057373, Learning Rate: 8.71105527638191e-05)
+
Train steps ... :  13%|█▎        | 13325/100000 [3:41:01<14:04:57,  1.71it/s]
Train steps ... :  13%|█▎        | 13326/100000 [3:41:01<14:05:14,  1.71it/s]
Train steps ... :  13%|█▎        | 13327/100000 [3:41:02<14:04:54,  1.71it/s]
Train steps ... :  13%|█▎        | 13328/100000 [3:41:02<14:05:22,  1.71it/s]
Train steps ... :  13%|█▎        | 13329/100000 [3:41:03<14:06:00,  1.71it/s]
Train steps ... :  13%|█▎        | 13330/100000 [3:41:04<14:05:54,  1.71it/s]
Train steps ... :  13%|█▎        | 13331/100000 [3:41:04<14:06:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13332/100000 [3:41:05<14:08:56,  1.70it/s]
Train steps ... :  13%|█▎        | 13333/100000 [3:41:05<14:05:09,  1.71it/s]
Train steps ... :  13%|█▎        | 13334/100000 [3:41:06<14:04:54,  1.71it/s]
Train steps ... :  13%|█▎        | 13335/100000 [3:41:06<14:07:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13336/100000 [3:41:07<14:04:00,  1.71it/s]
Train steps ... :  13%|█▎        | 13337/100000 [3:41:08<14:04:55,  1.71it/s]
Train steps ... :  13%|█▎        | 13338/100000 [3:41:08<14:05:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13339/100000 [3:41:09<14:05:17,  1.71it/s]
Train steps ... :  13%|█▎        | 13340/100000 [3:41:09<14:05:24,  1.71it/s]
Train steps ... :  13%|█▎        | 13341/100000 [3:41:10<14:05:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13342/100000 [3:41:11<14:05:29,  1.71it/s]
Train steps ... :  13%|█▎        | 13343/100000 [3:41:11<14:04:43,  1.71it/s]
Train steps ... :  13%|█▎        | 13344/100000 [3:41:12<14:06:55,  1.71it/s]
Train steps ... :  13%|█▎        | 13345/100000 [3:41:12<14:06:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13346/100000 [3:41:13<14:05:44,  1.71it/s]
Train steps ... :  13%|█▎        | 13347/100000 [3:41:14<14:05:49,  1.71it/s]
Train steps ... :  13%|█▎        | 13348/100000 [3:41:14<14:05:16,  1.71it/s]
Train steps ... :  13%|█▎        | 13349/100000 [3:41:15<14:05:32,  1.71it/s]
Train steps ... :  13%|█▎        | 13350/100000 [3:41:15<14:05:23,  1.71it/s]Step... (13350 / 100000 | Loss: 1.9403678178787231, Learning Rate: 8.70854271356784e-05)
+
                                                                             
Step... (13350 / 100000 | Loss: 1.4818733930587769, Learning Rate: 8.70854271356784e-05)
+
Train steps ... :  13%|█▎        | 13350/100000 [3:41:16<14:05:23,  1.71it/s]
Train steps ... :  13%|█▎        | 13351/100000 [3:41:16<14:04:37,  1.71it/s]
Train steps ... :  13%|█▎        | 13352/100000 [3:41:16<14:06:56,  1.71it/s]
Train steps ... :  13%|█▎        | 13353/100000 [3:41:17<14:04:35,  1.71it/s]
Train steps ... :  13%|█▎        | 13354/100000 [3:41:18<14:04:06,  1.71it/s]
Train steps ... :  13%|█▎        | 13355/100000 [3:41:18<14:03:23,  1.71it/s]
Train steps ... :  13%|█▎        | 13356/100000 [3:41:19<14:03:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13357/100000 [3:41:19<14:04:22,  1.71it/s]
Train steps ... :  13%|█▎        | 13358/100000 [3:41:20<14:04:07,  1.71it/s]
Train steps ... :  13%|█▎        | 13359/100000 [3:41:21<14:04:04,  1.71it/s]
Train steps ... :  13%|█▎        | 13360/100000 [3:41:21<14:04:32,  1.71it/s]
Train steps ... :  13%|█▎        | 13361/100000 [3:41:22<14:04:25,  1.71it/s]
Train steps ... :  13%|█▎        | 13362/100000 [3:41:22<14:04:09,  1.71it/s]
Train steps ... :  13%|█▎        | 13363/100000 [3:41:23<14:04:43,  1.71it/s]
Train steps ... :  13%|█▎        | 13364/100000 [3:41:23<14:05:07,  1.71it/s]
Train steps ... :  13%|█▎        | 13365/100000 [3:41:24<14:04:21,  1.71it/s]
Train steps ... :  13%|█▎        | 13366/100000 [3:41:25<14:04:11,  1.71it/s]
Train steps ... :  13%|█▎        | 13367/100000 [3:41:25<14:07:52,  1.70it/s]
Train steps ... :  13%|█▎        | 13368/100000 [3:41:26<14:05:44,  1.71it/s]
Train steps ... :  13%|█▎        | 13369/100000 [3:41:26<14:05:59,  1.71it/s]
Train steps ... :  13%|█▎        | 13370/100000 [3:41:27<14:05:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13371/100000 [3:41:28<14:05:54,  1.71it/s]
Train steps ... :  13%|█▎        | 13372/100000 [3:41:28<14:04:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13373/100000 [3:41:29<14:05:00,  1.71it/s]
Train steps ... :  13%|█▎        | 13374/100000 [3:41:29<14:04:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13375/100000 [3:41:30<14:05:08,  1.71it/s]Step... (13375 / 100000 | Loss: 0.7885533571243286, Learning Rate: 8.706030150753768e-05)
+
                                                                             
Step... (13375 / 100000 | Loss: 1.228994607925415, Learning Rate: 8.706030150753768e-05)
+
Train steps ... :  13%|█▎        | 13375/100000 [3:41:30<14:05:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13376/100000 [3:41:30<14:05:50,  1.71it/s]
Train steps ... :  13%|█▎        | 13377/100000 [3:41:31<14:06:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13378/100000 [3:41:32<14:05:46,  1.71it/s]
Train steps ... :  13%|█▎        | 13379/100000 [3:41:32<14:05:59,  1.71it/s]
Train steps ... :  13%|█▎        | 13380/100000 [3:41:33<14:08:45,  1.70it/s]
Train steps ... :  13%|█▎        | 13381/100000 [3:41:33<14:06:56,  1.70it/s]
Train steps ... :  13%|█▎        | 13382/100000 [3:41:34<14:08:24,  1.70it/s]
Train steps ... :  13%|█▎        | 13383/100000 [3:41:35<14:04:34,  1.71it/s]
Train steps ... :  13%|█▎        | 13384/100000 [3:41:35<14:05:21,  1.71it/s]
Train steps ... :  13%|█▎        | 13385/100000 [3:41:36<14:04:53,  1.71it/s]
Train steps ... :  13%|█▎        | 13386/100000 [3:41:36<14:04:12,  1.71it/s]
Train steps ... :  13%|█▎        | 13387/100000 [3:41:37<14:04:41,  1.71it/s]
Train steps ... :  13%|█▎        | 13388/100000 [3:41:38<14:05:38,  1.71it/s]
Train steps ... :  13%|█▎        | 13389/100000 [3:41:38<14:08:32,  1.70it/s]
Train steps ... :  13%|█▎        | 13390/100000 [3:41:39<14:07:20,  1.70it/s]
Train steps ... :  13%|█▎        | 13391/100000 [3:41:39<14:07:29,  1.70it/s]
Train steps ... :  13%|█▎        | 13392/100000 [3:41:40<14:06:03,  1.71it/s]
Train steps ... :  13%|█▎        | 13393/100000 [3:41:40<14:07:25,  1.70it/s]
Train steps ... :  13%|█▎        | 13394/100000 [3:41:41<14:05:27,  1.71it/s]
Train steps ... :  13%|█▎        | 13395/100000 [3:41:42<14:05:16,  1.71it/s]
Train steps ... :  13%|█▎        | 13396/100000 [3:41:42<14:03:50,  1.71it/s]
Train steps ... :  13%|█▎        | 13397/100000 [3:41:43<14:03:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13398/100000 [3:41:43<14:04:39,  1.71it/s]
Train steps ... :  13%|█▎        | 13399/100000 [3:41:44<14:02:33,  1.71it/s]
Train steps ... :  13%|█▎        | 13400/100000 [3:41:45<14:03:12,  1.71it/s]Step... (13400 / 100000 | Loss: 1.3870713710784912, Learning Rate: 8.7035175879397e-05)
+
                                                                             
Step... (13400 / 100000 | Loss: 1.106024980545044, Learning Rate: 8.7035175879397e-05)
+
Train steps ... :  13%|█▎        | 13400/100000 [3:41:45<14:03:12,  1.71it/s]
Train steps ... :  13%|█▎        | 13401/100000 [3:41:45<14:03:30,  1.71it/s]
Train steps ... :  13%|█▎        | 13402/100000 [3:41:46<14:03:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13403/100000 [3:41:46<14:02:47,  1.71it/s]
Train steps ... :  13%|█▎        | 13404/100000 [3:41:47<14:04:25,  1.71it/s]
Train steps ... :  13%|█▎        | 13405/100000 [3:41:47<14:04:55,  1.71it/s]
Train steps ... :  13%|█▎        | 13406/100000 [3:41:48<14:03:47,  1.71it/s]
Train steps ... :  13%|█▎        | 13407/100000 [3:41:49<14:04:26,  1.71it/s]
Train steps ... :  13%|█▎        | 13408/100000 [3:41:49<14:05:45,  1.71it/s]
Train steps ... :  13%|█▎        | 13409/100000 [3:41:50<14:03:20,  1.71it/s]
Train steps ... :  13%|█▎        | 13410/100000 [3:41:50<14:05:29,  1.71it/s]
Train steps ... :  13%|█▎        | 13411/100000 [3:41:51<14:03:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13412/100000 [3:41:52<14:02:49,  1.71it/s]
Train steps ... :  13%|█▎        | 13413/100000 [3:41:52<14:02:34,  1.71it/s]
Train steps ... :  13%|█▎        | 13414/100000 [3:41:53<14:02:31,  1.71it/s]
Train steps ... :  13%|█▎        | 13415/100000 [3:41:53<14:03:25,  1.71it/s]
Train steps ... :  13%|█▎        | 13416/100000 [3:41:54<14:03:44,  1.71it/s]
Train steps ... :  13%|█▎        | 13417/100000 [3:41:54<14:04:30,  1.71it/s]
Train steps ... :  13%|█▎        | 13418/100000 [3:41:55<14:05:17,  1.71it/s]
Train steps ... :  13%|█▎        | 13419/100000 [3:41:56<14:06:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13420/100000 [3:41:56<14:04:58,  1.71it/s]
Train steps ... :  13%|█▎        | 13421/100000 [3:41:57<14:03:20,  1.71it/s]
Train steps ... :  13%|█▎        | 13422/100000 [3:41:57<14:03:55,  1.71it/s]
Train steps ... :  13%|█▎        | 13423/100000 [3:41:58<14:05:08,  1.71it/s]
Train steps ... :  13%|█▎        | 13424/100000 [3:41:59<14:06:15,  1.71it/s]
Train steps ... :  13%|█▎        | 13425/100000 [3:41:59<14:05:25,  1.71it/s]Step... (13425 / 100000 | Loss: 1.014007329940796, Learning Rate: 8.701005025125628e-05)
+
                                                                             
Step... (13425 / 100000 | Loss: 1.0334608554840088, Learning Rate: 8.701005025125628e-05)
+
Train steps ... :  13%|█▎        | 13425/100000 [3:41:59<14:05:25,  1.71it/s]
Train steps ... :  13%|█▎        | 13426/100000 [3:42:00<14:05:52,  1.71it/s]
Train steps ... :  13%|█▎        | 13427/100000 [3:42:00<14:07:12,  1.70it/s]
Train steps ... :  13%|█▎        | 13428/100000 [3:42:01<14:06:25,  1.70it/s]
Train steps ... :  13%|█▎        | 13429/100000 [3:42:02<14:07:12,  1.70it/s]
Train steps ... :  13%|█▎        | 13430/100000 [3:42:02<14:05:46,  1.71it/s]
Train steps ... :  13%|█▎        | 13431/100000 [3:42:03<14:05:29,  1.71it/s]
Train steps ... :  13%|█▎        | 13432/100000 [3:42:03<14:06:41,  1.70it/s]
Train steps ... :  13%|█▎        | 13433/100000 [3:42:04<14:05:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13434/100000 [3:42:04<14:06:05,  1.71it/s]
Train steps ... :  13%|█▎        | 13435/100000 [3:42:05<14:06:41,  1.70it/s]
Train steps ... :  13%|█▎        | 13436/100000 [3:42:06<14:04:55,  1.71it/s]
Train steps ... :  13%|█▎        | 13437/100000 [3:42:06<14:05:32,  1.71it/s]
Train steps ... :  13%|█▎        | 13438/100000 [3:42:07<14:04:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13439/100000 [3:42:07<14:05:22,  1.71it/s]
Train steps ... :  13%|█▎        | 13440/100000 [3:42:08<14:05:25,  1.71it/s]
Train steps ... :  13%|█▎        | 13441/100000 [3:42:09<14:03:12,  1.71it/s]
Train steps ... :  13%|█▎        | 13442/100000 [3:42:09<14:05:01,  1.71it/s]
Train steps ... :  13%|█▎        | 13443/100000 [3:42:10<14:05:40,  1.71it/s]
Train steps ... :  13%|█▎        | 13444/100000 [3:42:10<14:05:24,  1.71it/s]
Train steps ... :  13%|█▎        | 13445/100000 [3:42:11<14:03:56,  1.71it/s]
Train steps ... :  13%|█▎        | 13446/100000 [3:42:11<14:04:12,  1.71it/s]
Train steps ... :  13%|█▎        | 13447/100000 [3:42:12<14:03:54,  1.71it/s]
Train steps ... :  13%|█▎        | 13448/100000 [3:42:13<14:04:51,  1.71it/s]
Train steps ... :  13%|█▎        | 13449/100000 [3:42:13<14:05:07,  1.71it/s]
Train steps ... :  13%|█▎        | 13450/100000 [3:42:14<14:04:33,  1.71it/s]Step... (13450 / 100000 | Loss: 1.1439781188964844, Learning Rate: 8.698492462311559e-05)
+
                                                                             
Step... (13450 / 100000 | Loss: 1.1997296810150146, Learning Rate: 8.698492462311559e-05)
+
Train steps ... :  13%|█▎        | 13450/100000 [3:42:14<14:04:33,  1.71it/s]
Train steps ... :  13%|█▎        | 13451/100000 [3:42:14<14:04:39,  1.71it/s]
Train steps ... :  13%|█▎        | 13452/100000 [3:42:15<14:04:33,  1.71it/s]
Train steps ... :  13%|█▎        | 13453/100000 [3:42:16<14:05:34,  1.71it/s]
Train steps ... :  13%|█▎        | 13454/100000 [3:42:16<14:05:44,  1.71it/s]
Train steps ... :  13%|█▎        | 13455/100000 [3:42:17<14:04:57,  1.71it/s]
Train steps ... :  13%|█▎        | 13456/100000 [3:42:17<14:05:38,  1.71it/s]
Train steps ... :  13%|█▎        | 13457/100000 [3:42:18<14:05:47,  1.71it/s]
Train steps ... :  13%|█▎        | 13458/100000 [3:42:19<14:06:29,  1.70it/s]
Train steps ... :  13%|█▎        | 13459/100000 [3:42:19<14:06:11,  1.70it/s]
Train steps ... :  13%|█▎        | 13460/100000 [3:42:20<14:05:50,  1.71it/s]
Train steps ... :  13%|█▎        | 13461/100000 [3:42:20<14:05:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13462/100000 [3:42:21<14:04:20,  1.71it/s]
Train steps ... :  13%|█▎        | 13463/100000 [3:42:21<14:04:20,  1.71it/s]
Train steps ... :  13%|█▎        | 13464/100000 [3:42:22<14:05:25,  1.71it/s]
Train steps ... :  13%|█▎        | 13465/100000 [3:42:23<14:05:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13466/100000 [3:42:23<14:06:01,  1.70it/s]
Train steps ... :  13%|█▎        | 13467/100000 [3:42:24<14:05:22,  1.71it/s]
Train steps ... :  13%|█▎        | 13468/100000 [3:42:24<14:05:46,  1.71it/s]
Train steps ... :  13%|█▎        | 13469/100000 [3:42:25<14:05:27,  1.71it/s]
Train steps ... :  13%|█▎        | 13470/100000 [3:42:26<14:05:48,  1.71it/s]
Train steps ... :  13%|█▎        | 13471/100000 [3:42:26<14:05:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13472/100000 [3:42:27<14:08:07,  1.70it/s]
Train steps ... :  13%|█▎        | 13473/100000 [3:42:27<14:04:16,  1.71it/s]
Train steps ... :  13%|█▎        | 13474/100000 [3:42:28<14:07:23,  1.70it/s]
Train steps ... :  13%|█▎        | 13475/100000 [3:42:28<14:07:17,  1.70it/s]Step... (13475 / 100000 | Loss: 0.8538151383399963, Learning Rate: 8.695979899497488e-05)
+
                                                                             
Step... (13475 / 100000 | Loss: 1.7293070554733276, Learning Rate: 8.695979899497488e-05)
+
Train steps ... :  13%|█▎        | 13475/100000 [3:42:29<14:07:17,  1.70it/s]
Train steps ... :  13%|█▎        | 13476/100000 [3:42:29<14:05:45,  1.71it/s]
Train steps ... :  13%|█▎        | 13477/100000 [3:42:30<14:04:06,  1.71it/s]
Train steps ... :  13%|█▎        | 13478/100000 [3:42:30<14:08:19,  1.70it/s]
Train steps ... :  13%|█▎        | 13479/100000 [3:42:31<14:03:38,  1.71it/s]
Train steps ... :  13%|█▎        | 13480/100000 [3:42:31<14:04:59,  1.71it/s]
Train steps ... :  13%|█▎        | 13481/100000 [3:42:32<14:04:36,  1.71it/s]
Train steps ... :  13%|█▎        | 13482/100000 [3:42:33<14:05:31,  1.71it/s]
Train steps ... :  13%|█▎        | 13483/100000 [3:42:33<14:06:48,  1.70it/s]
Train steps ... :  13%|█▎        | 13484/100000 [3:42:34<14:04:34,  1.71it/s]
Train steps ... :  13%|█▎        | 13485/100000 [3:42:34<14:05:48,  1.70it/s]
Train steps ... :  13%|█▎        | 13486/100000 [3:42:35<14:05:15,  1.71it/s]
Train steps ... :  13%|█▎        | 13487/100000 [3:42:36<14:04:49,  1.71it/s]
Train steps ... :  13%|█▎        | 13488/100000 [3:42:36<14:04:31,  1.71it/s]
Train steps ... :  13%|█▎        | 13489/100000 [3:42:37<14:05:03,  1.71it/s]
Train steps ... :  13%|█▎        | 13490/100000 [3:42:37<14:04:31,  1.71it/s]
Train steps ... :  13%|█▎        | 13491/100000 [3:42:38<14:03:24,  1.71it/s]
Train steps ... :  13%|█▎        | 13492/100000 [3:42:38<14:04:11,  1.71it/s]
Train steps ... :  13%|█▎        | 13493/100000 [3:42:39<14:03:03,  1.71it/s]
Train steps ... :  13%|█▎        | 13494/100000 [3:42:40<14:03:09,  1.71it/s]
Train steps ... :  13%|█▎        | 13495/100000 [3:42:40<14:02:42,  1.71it/s]
Train steps ... :  13%|█▎        | 13496/100000 [3:42:41<14:02:57,  1.71it/s]
Train steps ... :  13%|█▎        | 13497/100000 [3:42:41<14:02:53,  1.71it/s]
Train steps ... :  13%|█▎        | 13498/100000 [3:42:42<14:04:34,  1.71it/s]
Train steps ... :  13%|█▎        | 13499/100000 [3:42:43<14:04:58,  1.71it/s]
Train steps ... :  14%|█▎        | 13500/100000 [3:42:43<14:02:10,  1.71it/s]Step... (13500 / 100000 | Loss: 1.0884809494018555, Learning Rate: 8.693467336683418e-05)
+
                                                                             
Step... (13500 / 100000 | Loss: 1.6829888820648193, Learning Rate: 8.693467336683418e-05)
+
Train steps ... :  14%|█▎        | 13500/100000 [3:42:43<14:02:10,  1.71it/s]
Train steps ... :  14%|█▎        | 13501/100000 [3:42:44<14:01:54,  1.71it/s]
Train steps ... :  14%|█▎        | 13502/100000 [3:42:44<14:02:56,  1.71it/s]
Train steps ... :  14%|█▎        | 13503/100000 [3:42:45<14:02:25,  1.71it/s]
Train steps ... :  14%|█▎        | 13504/100000 [3:42:45<14:03:42,  1.71it/s]
Train steps ... :  14%|█▎        | 13505/100000 [3:42:46<14:06:49,  1.70it/s]
Train steps ... :  14%|█▎        | 13506/100000 [3:42:47<14:06:21,  1.70it/s]
Train steps ... :  14%|█▎        | 13507/100000 [3:42:47<14:05:39,  1.70it/s]
Train steps ... :  14%|█▎        | 13508/100000 [3:42:48<14:04:17,  1.71it/s]
Train steps ... :  14%|█▎        | 13509/100000 [3:42:48<14:04:28,  1.71it/s]
Train steps ... :  14%|█▎        | 13510/100000 [3:42:49<14:03:43,  1.71it/s]
Train steps ... :  14%|█▎        | 13511/100000 [3:42:50<14:03:21,  1.71it/s]
Train steps ... :  14%|█▎        | 13512/100000 [3:42:50<14:02:59,  1.71it/s]
Train steps ... :  14%|█▎        | 13513/100000 [3:42:51<14:03:26,  1.71it/s]
Train steps ... :  14%|█▎        | 13514/100000 [3:42:51<14:04:31,  1.71it/s]
Train steps ... :  14%|█▎        | 13515/100000 [3:42:52<14:02:30,  1.71it/s]
Train steps ... :  14%|█▎        | 13516/100000 [3:42:52<14:04:14,  1.71it/s]
Train steps ... :  14%|█▎        | 13517/100000 [3:42:53<14:02:40,  1.71it/s]
Train steps ... :  14%|█▎        | 13518/100000 [3:42:54<14:03:36,  1.71it/s]
Train steps ... :  14%|█▎        | 13519/100000 [3:42:54<14:03:20,  1.71it/s]
Train steps ... :  14%|█▎        | 13520/100000 [3:42:55<14:05:10,  1.71it/s]
Train steps ... :  14%|█▎        | 13521/100000 [3:42:55<14:06:09,  1.70it/s]
Train steps ... :  14%|█▎        | 13522/100000 [3:42:56<14:08:21,  1.70it/s]
Train steps ... :  14%|█▎        | 13523/100000 [3:42:57<14:08:04,  1.70it/s]
Train steps ... :  14%|█▎        | 13524/100000 [3:42:57<14:05:06,  1.71it/s]
Train steps ... :  14%|█▎        | 13525/100000 [3:42:58<14:06:13,  1.70it/s]Step... (13525 / 100000 | Loss: 1.417854905128479, Learning Rate: 8.690954773869348e-05)
+
                                                                             
Step... (13525 / 100000 | Loss: 1.3387657403945923, Learning Rate: 8.690954773869348e-05)
+
Train steps ... :  14%|█▎        | 13525/100000 [3:42:58<14:06:13,  1.70it/s]
Train steps ... :  14%|█▎        | 13526/100000 [3:42:58<14:06:24,  1.70it/s]
Train steps ... :  14%|█▎        | 13527/100000 [3:42:59<14:05:55,  1.70it/s]
Train steps ... :  14%|█▎        | 13528/100000 [3:43:00<14:04:04,  1.71it/s]
Train steps ... :  14%|█▎        | 13529/100000 [3:43:00<14:04:36,  1.71it/s]
Train steps ... :  14%|█▎        | 13530/100000 [3:43:01<14:06:02,  1.70it/s]
Train steps ... :  14%|█▎        | 13531/100000 [3:43:01<14:06:47,  1.70it/s]
Train steps ... :  14%|█▎        | 13532/100000 [3:43:02<14:04:45,  1.71it/s]
Train steps ... :  14%|█▎        | 13533/100000 [3:43:02<14:05:39,  1.70it/s]
Train steps ... :  14%|█▎        | 13534/100000 [3:43:03<14:07:09,  1.70it/s]
Train steps ... :  14%|█▎        | 13535/100000 [3:43:04<14:03:51,  1.71it/s]
Train steps ... :  14%|█▎        | 13536/100000 [3:43:04<14:06:51,  1.70it/s]
Train steps ... :  14%|█▎        | 13537/100000 [3:43:05<14:05:36,  1.70it/s]
Train steps ... :  14%|█▎        | 13538/100000 [3:43:05<14:02:49,  1.71it/s]
Train steps ... :  14%|█▎        | 13539/100000 [3:43:06<14:03:38,  1.71it/s]
Train steps ... :  14%|█▎        | 13540/100000 [3:43:07<14:03:30,  1.71it/s]
Train steps ... :  14%|█▎        | 13541/100000 [3:43:07<14:03:39,  1.71it/s]
Train steps ... :  14%|█▎        | 13542/100000 [3:43:08<14:04:31,  1.71it/s]
Train steps ... :  14%|█▎        | 13543/100000 [3:43:08<14:05:01,  1.71it/s]
Train steps ... :  14%|█▎        | 13544/100000 [3:43:09<14:06:44,  1.70it/s]
Train steps ... :  14%|█▎        | 13545/100000 [3:43:09<14:05:29,  1.70it/s]
Train steps ... :  14%|█▎        | 13546/100000 [3:43:10<14:05:50,  1.70it/s]
Train steps ... :  14%|█▎        | 13547/100000 [3:43:11<14:07:06,  1.70it/s]
Train steps ... :  14%|█▎        | 13548/100000 [3:43:11<14:07:38,  1.70it/s]
Train steps ... :  14%|█▎        | 13549/100000 [3:43:12<14:06:22,  1.70it/s]
Train steps ... :  14%|█▎        | 13550/100000 [3:43:12<14:05:45,  1.70it/s]Step... (13550 / 100000 | Loss: 1.3729428052902222, Learning Rate: 8.688442211055276e-05)
+
                                                                             
Step... (13550 / 100000 | Loss: 1.2932134866714478, Learning Rate: 8.688442211055276e-05)
+
Train steps ... :  14%|█▎        | 13550/100000 [3:43:13<14:05:45,  1.70it/s]
Train steps ... :  14%|█▎        | 13551/100000 [3:43:13<14:04:36,  1.71it/s]
Train steps ... :  14%|█▎        | 13552/100000 [3:43:14<14:03:18,  1.71it/s]
Train steps ... :  14%|█▎        | 13553/100000 [3:43:14<14:04:27,  1.71it/s]
Train steps ... :  14%|█▎        | 13554/100000 [3:43:15<14:03:58,  1.71it/s]
Train steps ... :  14%|█▎        | 13555/100000 [3:43:15<14:03:20,  1.71it/s]
Train steps ... :  14%|█▎        | 13556/100000 [3:43:16<14:02:42,  1.71it/s]
Train steps ... :  14%|█▎        | 13557/100000 [3:43:17<14:03:16,  1.71it/s]
Train steps ... :  14%|█▎        | 13558/100000 [3:43:17<14:02:23,  1.71it/s]
Train steps ... :  14%|█▎        | 13559/100000 [3:43:18<14:02:28,  1.71it/s]
Train steps ... :  14%|█▎        | 13560/100000 [3:43:18<14:02:26,  1.71it/s]
Train steps ... :  14%|█▎        | 13561/100000 [3:43:19<14:03:46,  1.71it/s]
Train steps ... :  14%|█▎        | 13562/100000 [3:43:19<14:03:03,  1.71it/s]
Train steps ... :  14%|█▎        | 13563/100000 [3:43:20<14:03:00,  1.71it/s]
Train steps ... :  14%|█▎        | 13564/100000 [3:43:21<14:03:48,  1.71it/s]
Train steps ... :  14%|█▎        | 13565/100000 [3:43:21<14:03:32,  1.71it/s]
Train steps ... :  14%|█▎        | 13566/100000 [3:43:22<14:04:17,  1.71it/s]
Train steps ... :  14%|█▎        | 13567/100000 [3:43:22<14:04:12,  1.71it/s]
Train steps ... :  14%|█▎        | 13568/100000 [3:43:23<14:04:53,  1.70it/s]
Train steps ... :  14%|█▎        | 13569/100000 [3:43:24<14:05:12,  1.70it/s]
Train steps ... :  14%|█▎        | 13570/100000 [3:43:24<14:04:42,  1.71it/s]
Train steps ... :  14%|█▎        | 13571/100000 [3:43:25<14:04:14,  1.71it/s]
Train steps ... :  14%|█▎        | 13572/100000 [3:43:25<14:04:58,  1.70it/s]
Train steps ... :  14%|█▎        | 13573/100000 [3:43:26<14:03:09,  1.71it/s]
Train steps ... :  14%|█▎        | 13574/100000 [3:43:26<14:03:13,  1.71it/s]
Train steps ... :  14%|█▎        | 13575/100000 [3:43:27<14:03:56,  1.71it/s]Step... (13575 / 100000 | Loss: 1.0821306705474854, Learning Rate: 8.685929648241207e-05)
+
                                                                             
Step... (13575 / 100000 | Loss: 1.409106969833374, Learning Rate: 8.685929648241207e-05)
+
Train steps ... :  14%|█▎        | 13575/100000 [3:43:27<14:03:56,  1.71it/s]
Train steps ... :  14%|█▎        | 13576/100000 [3:43:28<14:05:13,  1.70it/s]
Train steps ... :  14%|█▎        | 13577/100000 [3:43:28<14:04:03,  1.71it/s]
Train steps ... :  14%|█▎        | 13578/100000 [3:43:29<14:05:29,  1.70it/s]
Train steps ... :  14%|█▎        | 13579/100000 [3:43:29<14:05:11,  1.70it/s]
Train steps ... :  14%|█▎        | 13580/100000 [3:43:30<14:04:56,  1.70it/s]
Train steps ... :  14%|█▎        | 13581/100000 [3:43:31<14:04:33,  1.71it/s]
Train steps ... :  14%|█▎        | 13582/100000 [3:43:31<14:03:52,  1.71it/s]
Train steps ... :  14%|█▎        | 13583/100000 [3:43:32<14:02:50,  1.71it/s]
Train steps ... :  14%|█▎        | 13584/100000 [3:43:32<14:03:24,  1.71it/s]
Train steps ... :  14%|█▎        | 13585/100000 [3:43:33<14:03:36,  1.71it/s]
Train steps ... :  14%|█▎        | 13586/100000 [3:43:34<14:04:18,  1.71it/s]
Train steps ... :  14%|█▎        | 13587/100000 [3:43:34<14:04:42,  1.70it/s]
Train steps ... :  14%|█▎        | 13588/100000 [3:43:35<14:04:49,  1.70it/s]
Train steps ... :  14%|█▎        | 13589/100000 [3:43:35<14:02:12,  1.71it/s]
Train steps ... :  14%|█▎        | 13590/100000 [3:43:36<14:03:24,  1.71it/s]
Train steps ... :  14%|█▎        | 13591/100000 [3:43:36<14:03:17,  1.71it/s]
Train steps ... :  14%|█▎        | 13592/100000 [3:43:37<14:02:27,  1.71it/s]
Train steps ... :  14%|█▎        | 13593/100000 [3:43:38<14:02:10,  1.71it/s]
Train steps ... :  14%|█▎        | 13594/100000 [3:43:38<14:02:55,  1.71it/s]
Train steps ... :  14%|█▎        | 13595/100000 [3:43:39<14:03:03,  1.71it/s]
Train steps ... :  14%|█▎        | 13596/100000 [3:43:39<14:03:15,  1.71it/s]
Train steps ... :  14%|█▎        | 13597/100000 [3:43:40<14:03:34,  1.71it/s]
Train steps ... :  14%|█▎        | 13598/100000 [3:43:41<14:05:13,  1.70it/s]
Train steps ... :  14%|█▎        | 13599/100000 [3:43:41<14:04:57,  1.70it/s]
Train steps ... :  14%|█▎        | 13600/100000 [3:43:42<14:03:50,  1.71it/s]Step... (13600 / 100000 | Loss: 1.220249891281128, Learning Rate: 8.683417085427135e-05)
+
                                                                             
Step... (13600 / 100000 | Loss: 1.964200735092163, Learning Rate: 8.683417085427135e-05)
+
Train steps ... :  14%|█▎        | 13600/100000 [3:43:42<14:03:50,  1.71it/s]
Train steps ... :  14%|█▎        | 13601/100000 [3:43:42<14:04:10,  1.71it/s]
Train steps ... :  14%|█▎        | 13602/100000 [3:43:43<14:04:20,  1.71it/s]
Train steps ... :  14%|█▎        | 13603/100000 [3:43:43<14:06:57,  1.70it/s]
Train steps ... :  14%|█▎        | 13604/100000 [3:43:44<14:04:42,  1.70it/s]
Train steps ... :  14%|█▎        | 13605/100000 [3:43:45<14:03:51,  1.71it/s]
Train steps ... :  14%|█▎        | 13606/100000 [3:43:45<14:03:57,  1.71it/s]
Train steps ... :  14%|█▎        | 13607/100000 [3:43:46<14:03:25,  1.71it/s]
Train steps ... :  14%|█▎        | 13608/100000 [3:43:46<14:04:08,  1.71it/s]
Train steps ... :  14%|█▎        | 13609/100000 [3:43:47<14:04:59,  1.70it/s]
Train steps ... :  14%|█▎        | 13610/100000 [3:43:48<14:05:39,  1.70it/s]
Train steps ... :  14%|█▎        | 13611/100000 [3:43:48<14:03:36,  1.71it/s]
Train steps ... :  14%|█▎        | 13612/100000 [3:43:49<14:02:37,  1.71it/s]
Train steps ... :  14%|█▎        | 13613/100000 [3:43:49<14:05:01,  1.70it/s]
Train steps ... :  14%|█▎        | 13614/100000 [3:43:50<14:04:23,  1.71it/s]
Train steps ... :  14%|█▎        | 13615/100000 [3:43:51<14:04:01,  1.71it/s]
Train steps ... :  14%|█▎        | 13616/100000 [3:43:51<14:03:31,  1.71it/s]
Train steps ... :  14%|█▎        | 13617/100000 [3:43:52<14:03:49,  1.71it/s]
Train steps ... :  14%|█▎        | 13618/100000 [3:43:52<14:04:07,  1.71it/s]
Train steps ... :  14%|█▎        | 13619/100000 [3:43:53<14:03:59,  1.71it/s]
Train steps ... :  14%|█▎        | 13620/100000 [3:43:53<14:05:05,  1.70it/s]
Train steps ... :  14%|█▎        | 13621/100000 [3:43:54<14:04:30,  1.70it/s]
Train steps ... :  14%|█▎        | 13622/100000 [3:43:55<14:04:27,  1.70it/s]
Train steps ... :  14%|█▎        | 13623/100000 [3:43:55<14:03:03,  1.71it/s]
Train steps ... :  14%|█▎        | 13624/100000 [3:43:56<14:03:41,  1.71it/s]
Train steps ... :  14%|█▎        | 13625/100000 [3:43:56<14:05:35,  1.70it/s]Step... (13625 / 100000 | Loss: 1.4129269123077393, Learning Rate: 8.680904522613066e-05)
+
                                                                             
Step... (13625 / 100000 | Loss: 1.0175179243087769, Learning Rate: 8.680904522613066e-05)
+
Train steps ... :  14%|█▎        | 13625/100000 [3:43:57<14:05:35,  1.70it/s]
Train steps ... :  14%|█▎        | 13626/100000 [3:43:57<14:06:07,  1.70it/s]
Train steps ... :  14%|█▎        | 13627/100000 [3:43:58<14:04:29,  1.70it/s]
Train steps ... :  14%|█▎        | 13628/100000 [3:43:58<14:04:47,  1.70it/s]
Train steps ... :  14%|█▎        | 13629/100000 [3:43:59<14:04:01,  1.71it/s]
Train steps ... :  14%|█▎        | 13630/100000 [3:43:59<14:05:03,  1.70it/s]
Train steps ... :  14%|█▎        | 13631/100000 [3:44:00<14:05:27,  1.70it/s]
Train steps ... :  14%|█▎        | 13632/100000 [3:44:01<14:11:09,  1.69it/s]
Train steps ... :  14%|█▎        | 13633/100000 [3:44:01<14:07:33,  1.70it/s]
Train steps ... :  14%|█▎        | 13634/100000 [3:44:02<14:07:54,  1.70it/s]
Train steps ... :  14%|█▎        | 13635/100000 [3:44:02<14:05:53,  1.70it/s]
Train steps ... :  14%|█▎        | 13636/100000 [3:44:03<14:05:41,  1.70it/s]
Train steps ... :  14%|█▎        | 13637/100000 [3:44:03<14:03:35,  1.71it/s]
Train steps ... :  14%|█▎        | 13638/100000 [3:44:04<14:04:46,  1.70it/s]
Train steps ... :  14%|█▎        | 13639/100000 [3:44:05<14:03:38,  1.71it/s]
Train steps ... :  14%|█▎        | 13640/100000 [3:44:05<14:04:28,  1.70it/s]
Train steps ... :  14%|█▎        | 13641/100000 [3:44:06<14:05:29,  1.70it/s]
Train steps ... :  14%|█▎        | 13642/100000 [3:44:06<14:02:41,  1.71it/s]
Train steps ... :  14%|█▎        | 13643/100000 [3:44:07<14:04:17,  1.70it/s]
Train steps ... :  14%|█▎        | 13644/100000 [3:44:08<14:01:37,  1.71it/s]
Train steps ... :  14%|█▎        | 13645/100000 [3:44:08<14:01:11,  1.71it/s]
Train steps ... :  14%|█▎        | 13646/100000 [3:44:09<14:04:56,  1.70it/s]
Train steps ... :  14%|█▎        | 13647/100000 [3:44:09<14:02:40,  1.71it/s]
Train steps ... :  14%|█▎        | 13648/100000 [3:44:10<14:03:18,  1.71it/s]
Train steps ... :  14%|█▎        | 13649/100000 [3:44:10<14:07:26,  1.70it/s]
Train steps ... :  14%|█▎        | 13650/100000 [3:44:11<14:03:51,  1.71it/s]Step... (13650 / 100000 | Loss: 1.1787810325622559, Learning Rate: 8.678391959798995e-05)
+
                                                                             
Step... (13650 / 100000 | Loss: 0.7742452621459961, Learning Rate: 8.678391959798995e-05)
+
Train steps ... :  14%|█▎        | 13650/100000 [3:44:11<14:03:51,  1.71it/s]
Train steps ... :  14%|█▎        | 13651/100000 [3:44:12<14:04:35,  1.70it/s]
Train steps ... :  14%|█▎        | 13652/100000 [3:44:12<14:02:47,  1.71it/s]
Train steps ... :  14%|█▎        | 13653/100000 [3:44:13<14:03:14,  1.71it/s]
Train steps ... :  14%|█▎        | 13654/100000 [3:44:13<14:04:25,  1.70it/s]
Train steps ... :  14%|█▎        | 13655/100000 [3:44:14<14:03:13,  1.71it/s]
Train steps ... :  14%|█▎        | 13656/100000 [3:44:15<14:05:59,  1.70it/s]
Train steps ... :  14%|█▎        | 13657/100000 [3:44:15<14:06:31,  1.70it/s]
Train steps ... :  14%|█▎        | 13658/100000 [3:44:16<14:04:14,  1.70it/s]
Train steps ... :  14%|█▎        | 13659/100000 [3:44:16<14:04:54,  1.70it/s]
Train steps ... :  14%|█▎        | 13660/100000 [3:44:17<14:03:25,  1.71it/s]
Train steps ... :  14%|█▎        | 13661/100000 [3:44:18<14:04:43,  1.70it/s]
Train steps ... :  14%|█▎        | 13662/100000 [3:44:18<14:05:05,  1.70it/s]
Train steps ... :  14%|█▎        | 13663/100000 [3:44:19<14:04:21,  1.70it/s]
Train steps ... :  14%|█▎        | 13664/100000 [3:44:19<14:04:18,  1.70it/s]
Train steps ... :  14%|█▎        | 13665/100000 [3:44:20<14:04:48,  1.70it/s]
Train steps ... :  14%|█▎        | 13666/100000 [3:44:20<14:02:31,  1.71it/s]
Train steps ... :  14%|█▎        | 13667/100000 [3:44:21<14:03:38,  1.71it/s]
Train steps ... :  14%|█▎        | 13668/100000 [3:44:22<14:01:28,  1.71it/s]
Train steps ... :  14%|█▎        | 13669/100000 [3:44:22<14:02:00,  1.71it/s]
Train steps ... :  14%|█▎        | 13670/100000 [3:44:23<14:02:30,  1.71it/s]
Train steps ... :  14%|█▎        | 13671/100000 [3:44:23<14:03:44,  1.71it/s]
Train steps ... :  14%|█▎        | 13672/100000 [3:44:24<14:04:03,  1.70it/s]
Train steps ... :  14%|█▎        | 13673/100000 [3:44:25<14:03:59,  1.70it/s]
Train steps ... :  14%|█▎        | 13674/100000 [3:44:25<14:04:26,  1.70it/s]
Train steps ... :  14%|█▎        | 13675/100000 [3:44:26<14:02:30,  1.71it/s]Step... (13675 / 100000 | Loss: 1.176961898803711, Learning Rate: 8.675879396984926e-05)
+
                                                                             
Step... (13675 / 100000 | Loss: 1.2261919975280762, Learning Rate: 8.675879396984926e-05)
+
Train steps ... :  14%|█▎        | 13675/100000 [3:44:26<14:02:30,  1.71it/s]
Train steps ... :  14%|█▎        | 13676/100000 [3:44:26<14:03:18,  1.71it/s]
Train steps ... :  14%|█▎        | 13677/100000 [3:44:27<14:01:34,  1.71it/s]
Train steps ... :  14%|█▎        | 13678/100000 [3:44:27<14:02:53,  1.71it/s]
Train steps ... :  14%|█▎        | 13679/100000 [3:44:28<14:02:56,  1.71it/s]
Train steps ... :  14%|█▎        | 13680/100000 [3:44:29<14:02:50,  1.71it/s]
Train steps ... :  14%|█▎        | 13681/100000 [3:44:29<14:02:42,  1.71it/s]
Train steps ... :  14%|█▎        | 13682/100000 [3:44:30<14:02:10,  1.71it/s]
Train steps ... :  14%|█▎        | 13683/100000 [3:44:30<14:03:18,  1.71it/s]
Train steps ... :  14%|█▎        | 13684/100000 [3:44:31<14:02:50,  1.71it/s]
Train steps ... :  14%|█▎        | 13685/100000 [3:44:32<14:02:27,  1.71it/s]
Train steps ... :  14%|█▎        | 13686/100000 [3:44:32<14:02:42,  1.71it/s]
Train steps ... :  14%|█▎        | 13687/100000 [3:44:33<14:03:16,  1.71it/s]
Train steps ... :  14%|█▎        | 13688/100000 [3:44:33<14:02:37,  1.71it/s]
Train steps ... :  14%|█▎        | 13689/100000 [3:44:34<14:02:01,  1.71it/s]
Train steps ... :  14%|█▎        | 13690/100000 [3:44:34<14:01:06,  1.71it/s]
Train steps ... :  14%|█▎        | 13691/100000 [3:44:35<14:01:31,  1.71it/s]
Train steps ... :  14%|█▎        | 13692/100000 [3:44:36<14:05:05,  1.70it/s]
Train steps ... :  14%|█▎        | 13693/100000 [3:44:36<14:04:12,  1.70it/s]
Train steps ... :  14%|█▎        | 13694/100000 [3:44:37<14:04:38,  1.70it/s]
Train steps ... :  14%|█▎        | 13695/100000 [3:44:37<14:02:09,  1.71it/s]
Train steps ... :  14%|█▎        | 13696/100000 [3:44:38<14:01:19,  1.71it/s]
Train steps ... :  14%|█▎        | 13697/100000 [3:44:39<14:02:02,  1.71it/s]
Train steps ... :  14%|█▎        | 13698/100000 [3:44:39<14:01:06,  1.71it/s]
Train steps ... :  14%|█▎        | 13699/100000 [3:44:40<14:01:28,  1.71it/s]
Train steps ... :  14%|█▎        | 13700/100000 [3:44:40<14:02:01,  1.71it/s]Step... (13700 / 100000 | Loss: 0.957644522190094, Learning Rate: 8.673366834170855e-05)
+
                                                                             
Step... (13700 / 100000 | Loss: 1.1322559118270874, Learning Rate: 8.673366834170855e-05)
+
Train steps ... :  14%|█▎        | 13700/100000 [3:44:41<14:02:01,  1.71it/s]
Train steps ... :  14%|█▎        | 13701/100000 [3:44:41<14:03:24,  1.71it/s]
Train steps ... :  14%|█▎        | 13702/100000 [3:44:42<14:03:08,  1.71it/s]
Train steps ... :  14%|█▎        | 13703/100000 [3:44:42<14:02:25,  1.71it/s]
Train steps ... :  14%|█▎        | 13704/100000 [3:44:43<14:02:21,  1.71it/s]
Train steps ... :  14%|█▎        | 13705/100000 [3:44:43<14:02:19,  1.71it/s]
Train steps ... :  14%|█▎        | 13706/100000 [3:44:44<14:03:12,  1.71it/s]
Train steps ... :  14%|█▎        | 13707/100000 [3:44:44<14:01:56,  1.71it/s]
Train steps ... :  14%|█▎        | 13708/100000 [3:44:45<14:01:21,  1.71it/s]
Train steps ... :  14%|█▎        | 13709/100000 [3:44:46<14:02:49,  1.71it/s]
Train steps ... :  14%|█▎        | 13710/100000 [3:44:46<14:05:15,  1.70it/s]
Train steps ... :  14%|█▎        | 13711/100000 [3:44:47<14:01:44,  1.71it/s]
Train steps ... :  14%|█▎        | 13712/100000 [3:44:47<14:02:20,  1.71it/s]
Train steps ... :  14%|█▎        | 13713/100000 [3:44:48<14:01:29,  1.71it/s]
Train steps ... :  14%|█▎        | 13714/100000 [3:44:49<14:00:12,  1.71it/s]
Train steps ... :  14%|█▎        | 13715/100000 [3:44:49<14:02:05,  1.71it/s]
Train steps ... :  14%|█▎        | 13716/100000 [3:44:50<14:03:48,  1.70it/s]
Train steps ... :  14%|█▎        | 13717/100000 [3:44:50<14:02:43,  1.71it/s]
Train steps ... :  14%|█▎        | 13718/100000 [3:44:51<14:02:53,  1.71it/s]
Train steps ... :  14%|█▎        | 13719/100000 [3:44:51<14:01:54,  1.71it/s]
Train steps ... :  14%|█▎        | 13720/100000 [3:44:52<14:03:24,  1.70it/s]
Train steps ... :  14%|█▎        | 13721/100000 [3:44:53<14:02:46,  1.71it/s]
Train steps ... :  14%|█▎        | 13722/100000 [3:44:53<14:03:43,  1.70it/s]
Train steps ... :  14%|█▎        | 13723/100000 [3:44:54<14:03:25,  1.70it/s]
Train steps ... :  14%|█▎        | 13724/100000 [3:44:54<14:03:03,  1.71it/s]
Train steps ... :  14%|█▎        | 13725/100000 [3:44:55<14:02:42,  1.71it/s]Step... (13725 / 100000 | Loss: 1.0295099020004272, Learning Rate: 8.670854271356784e-05)
+
                                                                             
Step... (13725 / 100000 | Loss: 1.332619309425354, Learning Rate: 8.670854271356784e-05)
+
Train steps ... :  14%|█▎        | 13725/100000 [3:44:55<14:02:42,  1.71it/s]
Train steps ... :  14%|█▎        | 13726/100000 [3:44:56<14:05:24,  1.70it/s]
Train steps ... :  14%|█▎        | 13727/100000 [3:44:56<14:04:39,  1.70it/s]
Train steps ... :  14%|█▎        | 13728/100000 [3:44:57<14:01:28,  1.71it/s]
Train steps ... :  14%|█▎        | 13729/100000 [3:44:57<14:01:32,  1.71it/s]
Train steps ... :  14%|█▎        | 13730/100000 [3:44:58<14:01:44,  1.71it/s]
Train steps ... :  14%|█▎        | 13731/100000 [3:44:59<14:01:53,  1.71it/s]
Train steps ... :  14%|█▎        | 13732/100000 [3:44:59<14:02:00,  1.71it/s]
Train steps ... :  14%|█▎        | 13733/100000 [3:45:00<14:04:20,  1.70it/s]
Train steps ... :  14%|█▎        | 13734/100000 [3:45:00<14:04:21,  1.70it/s]
Train steps ... :  14%|█▎        | 13735/100000 [3:45:01<14:02:51,  1.71it/s]
Train steps ... :  14%|█▎        | 13736/100000 [3:45:01<14:03:02,  1.71it/s]
Train steps ... :  14%|█▎        | 13737/100000 [3:45:02<14:02:38,  1.71it/s]
Train steps ... :  14%|█▎        | 13738/100000 [3:45:03<14:02:25,  1.71it/s]
Train steps ... :  14%|█▎        | 13739/100000 [3:45:03<14:02:53,  1.71it/s]
Train steps ... :  14%|█▎        | 13740/100000 [3:45:04<14:02:46,  1.71it/s]
Train steps ... :  14%|█▎        | 13741/100000 [3:45:04<14:03:16,  1.70it/s]
Train steps ... :  14%|█▎        | 13742/100000 [3:45:05<14:01:23,  1.71it/s]
Train steps ... :  14%|█▎        | 13743/100000 [3:45:06<14:01:28,  1.71it/s]
Train steps ... :  14%|█▎        | 13744/100000 [3:45:06<14:04:38,  1.70it/s]
Train steps ... :  14%|█▎        | 13745/100000 [3:45:07<14:01:48,  1.71it/s]
Train steps ... :  14%|█▎        | 13746/100000 [3:45:07<14:06:14,  1.70it/s]
Train steps ... :  14%|█▎        | 13747/100000 [3:45:08<14:02:47,  1.71it/s]
Train steps ... :  14%|█▎        | 13748/100000 [3:45:08<14:01:29,  1.71it/s]
Train steps ... :  14%|█▎        | 13749/100000 [3:45:09<14:03:54,  1.70it/s]
Train steps ... :  14%|█▍        | 13750/100000 [3:45:10<14:03:05,  1.71it/s]Step... (13750 / 100000 | Loss: 1.1445943117141724, Learning Rate: 8.668341708542715e-05)
+
                                                                             
Step... (13750 / 100000 | Loss: 1.0495121479034424, Learning Rate: 8.668341708542715e-05)
+
Train steps ... :  14%|█▍        | 13750/100000 [3:45:10<14:03:05,  1.71it/s]
Train steps ... :  14%|█▍        | 13751/100000 [3:45:10<14:02:53,  1.71it/s]
Train steps ... :  14%|█▍        | 13752/100000 [3:45:11<14:03:15,  1.70it/s]
Train steps ... :  14%|█▍        | 13753/100000 [3:45:11<14:05:59,  1.70it/s]
Train steps ... :  14%|█▍        | 13754/100000 [3:45:12<14:05:05,  1.70it/s]
Train steps ... :  14%|█▍        | 13755/100000 [3:45:13<14:02:59,  1.71it/s]
Train steps ... :  14%|█▍        | 13756/100000 [3:45:13<14:01:54,  1.71it/s]
Train steps ... :  14%|█▍        | 13757/100000 [3:45:14<14:03:52,  1.70it/s]
Train steps ... :  14%|█▍        | 13758/100000 [3:45:14<14:04:05,  1.70it/s]
Train steps ... :  14%|█▍        | 13759/100000 [3:45:15<14:04:14,  1.70it/s]
Train steps ... :  14%|█▍        | 13760/100000 [3:45:16<14:01:19,  1.71it/s]
Train steps ... :  14%|█▍        | 13761/100000 [3:45:16<14:02:56,  1.71it/s]
Train steps ... :  14%|█▍        | 13762/100000 [3:45:17<14:00:05,  1.71it/s]
Train steps ... :  14%|█▍        | 13763/100000 [3:45:17<14:01:40,  1.71it/s]
Train steps ... :  14%|█▍        | 13764/100000 [3:45:18<14:02:59,  1.70it/s]
Train steps ... :  14%|█▍        | 13765/100000 [3:45:18<14:01:58,  1.71it/s]
Train steps ... :  14%|█▍        | 13766/100000 [3:45:19<14:00:52,  1.71it/s]
Train steps ... :  14%|█▍        | 13767/100000 [3:45:20<14:05:10,  1.70it/s]
Train steps ... :  14%|█▍        | 13768/100000 [3:45:20<14:03:26,  1.70it/s]
Train steps ... :  14%|█▍        | 13769/100000 [3:45:21<14:01:47,  1.71it/s]
Train steps ... :  14%|█▍        | 13770/100000 [3:45:21<14:02:24,  1.71it/s]
Train steps ... :  14%|█▍        | 13771/100000 [3:45:22<14:02:05,  1.71it/s]
Train steps ... :  14%|█▍        | 13772/100000 [3:45:23<14:03:17,  1.70it/s]
Train steps ... :  14%|█▍        | 13773/100000 [3:45:23<14:02:26,  1.71it/s]
Train steps ... :  14%|█▍        | 13774/100000 [3:45:24<14:03:24,  1.70it/s]
Train steps ... :  14%|█▍        | 13775/100000 [3:45:24<14:00:54,  1.71it/s]Step... (13775 / 100000 | Loss: 0.8882344961166382, Learning Rate: 8.665829145728643e-05)
+
                                                                             
Step... (13775 / 100000 | Loss: 1.2027966976165771, Learning Rate: 8.665829145728643e-05)
+
Train steps ... :  14%|█▍        | 13775/100000 [3:45:25<14:00:54,  1.71it/s]
Train steps ... :  14%|█▍        | 13776/100000 [3:45:25<14:01:43,  1.71it/s]
Train steps ... :  14%|█▍        | 13777/100000 [3:45:26<14:04:07,  1.70it/s]
Train steps ... :  14%|█▍        | 13778/100000 [3:45:26<14:05:46,  1.70it/s]
Train steps ... :  14%|█▍        | 13779/100000 [3:45:27<14:03:41,  1.70it/s]
Train steps ... :  14%|█▍        | 13780/100000 [3:45:27<14:04:34,  1.70it/s]
Train steps ... :  14%|█▍        | 13781/100000 [3:45:28<14:01:06,  1.71it/s]
Train steps ... :  14%|█▍        | 13782/100000 [3:45:28<14:02:02,  1.71it/s]
Train steps ... :  14%|█▍        | 13783/100000 [3:45:29<14:01:41,  1.71it/s]
Train steps ... :  14%|█▍        | 13784/100000 [3:45:30<14:01:10,  1.71it/s]
Train steps ... :  14%|█▍        | 13785/100000 [3:45:30<14:01:01,  1.71it/s]
Train steps ... :  14%|█▍        | 13786/100000 [3:45:31<14:01:06,  1.71it/s]
Train steps ... :  14%|█▍        | 13787/100000 [3:45:31<14:01:09,  1.71it/s]
Train steps ... :  14%|█▍        | 13788/100000 [3:45:32<14:02:52,  1.70it/s]
Train steps ... :  14%|█▍        | 13789/100000 [3:45:33<14:01:10,  1.71it/s]
Train steps ... :  14%|█▍        | 13790/100000 [3:45:33<14:01:05,  1.71it/s]
Train steps ... :  14%|█▍        | 13791/100000 [3:45:34<14:01:03,  1.71it/s]
Train steps ... :  14%|█▍        | 13792/100000 [3:45:34<14:03:52,  1.70it/s]
Train steps ... :  14%|█▍        | 13793/100000 [3:45:35<14:01:17,  1.71it/s]
Train steps ... :  14%|█▍        | 13794/100000 [3:45:35<14:02:35,  1.71it/s]
Train steps ... :  14%|█▍        | 13795/100000 [3:45:36<14:01:59,  1.71it/s]
Train steps ... :  14%|█▍        | 13796/100000 [3:45:37<14:01:19,  1.71it/s]
Train steps ... :  14%|█▍        | 13797/100000 [3:45:37<14:00:06,  1.71it/s]
Train steps ... :  14%|█▍        | 13798/100000 [3:45:38<14:00:53,  1.71it/s]
Train steps ... :  14%|█▍        | 13799/100000 [3:45:38<14:02:49,  1.70it/s]
Train steps ... :  14%|█▍        | 13800/100000 [3:45:39<14:02:16,  1.71it/s]Step... (13800 / 100000 | Loss: 1.536987066268921, Learning Rate: 8.663316582914574e-05)
+
                                                                             
Step... (13800 / 100000 | Loss: 1.0633506774902344, Learning Rate: 8.663316582914574e-05)
+
Train steps ... :  14%|█▍        | 13800/100000 [3:45:39<14:02:16,  1.71it/s]
Train steps ... :  14%|█▍        | 13801/100000 [3:45:40<14:01:55,  1.71it/s]
Train steps ... :  14%|█▍        | 13802/100000 [3:45:40<14:00:47,  1.71it/s]
Train steps ... :  14%|█▍        | 13803/100000 [3:45:41<14:03:43,  1.70it/s]
Train steps ... :  14%|█▍        | 13804/100000 [3:45:41<14:02:28,  1.71it/s]
Train steps ... :  14%|█▍        | 13805/100000 [3:45:42<14:02:08,  1.71it/s]
Train steps ... :  14%|█▍        | 13806/100000 [3:45:42<14:03:45,  1.70it/s]
Train steps ... :  14%|█▍        | 13807/100000 [3:45:43<14:01:25,  1.71it/s]
Train steps ... :  14%|█▍        | 13808/100000 [3:45:44<14:00:05,  1.71it/s]
Train steps ... :  14%|█▍        | 13809/100000 [3:45:44<14:01:37,  1.71it/s]
Train steps ... :  14%|█▍        | 13810/100000 [3:45:45<14:01:25,  1.71it/s]
Train steps ... :  14%|█▍        | 13811/100000 [3:45:45<14:02:28,  1.71it/s]
Train steps ... :  14%|█▍        | 13812/100000 [3:45:46<13:59:19,  1.71it/s]
Train steps ... :  14%|█▍        | 13813/100000 [3:45:47<14:00:53,  1.71it/s]
Train steps ... :  14%|█▍        | 13814/100000 [3:45:47<13:59:56,  1.71it/s]
Train steps ... :  14%|█▍        | 13815/100000 [3:45:48<14:00:33,  1.71it/s]
Train steps ... :  14%|█▍        | 13816/100000 [3:45:48<14:01:46,  1.71it/s]
Train steps ... :  14%|█▍        | 13817/100000 [3:45:49<14:00:57,  1.71it/s]
Train steps ... :  14%|█▍        | 13818/100000 [3:45:50<14:01:57,  1.71it/s]
Train steps ... :  14%|█▍        | 13819/100000 [3:45:50<14:02:28,  1.70it/s]
Train steps ... :  14%|█▍        | 13820/100000 [3:45:51<14:03:12,  1.70it/s]
Train steps ... :  14%|█▍        | 13821/100000 [3:45:51<14:02:53,  1.70it/s]
Train steps ... :  14%|█▍        | 13822/100000 [3:45:52<14:01:38,  1.71it/s]
Train steps ... :  14%|█▍        | 13823/100000 [3:45:52<14:03:25,  1.70it/s]
Train steps ... :  14%|█▍        | 13824/100000 [3:45:53<14:00:28,  1.71it/s]
Train steps ... :  14%|█▍        | 13825/100000 [3:45:54<13:58:38,  1.71it/s]Step... (13825 / 100000 | Loss: 1.554135799407959, Learning Rate: 8.660804020100502e-05)
+
                                                                             
Step... (13825 / 100000 | Loss: 1.0365291833877563, Learning Rate: 8.660804020100502e-05)
+
Train steps ... :  14%|█▍        | 13825/100000 [3:45:54<13:58:38,  1.71it/s]
Train steps ... :  14%|█▍        | 13826/100000 [3:45:54<14:01:27,  1.71it/s]
Train steps ... :  14%|█▍        | 13827/100000 [3:45:55<14:02:29,  1.70it/s]
Train steps ... :  14%|█▍        | 13828/100000 [3:45:55<14:00:43,  1.71it/s]
Train steps ... :  14%|█▍        | 13829/100000 [3:45:56<14:02:49,  1.70it/s]
Train steps ... :  14%|█▍        | 13830/100000 [3:45:57<14:01:28,  1.71it/s]
Train steps ... :  14%|█▍        | 13831/100000 [3:45:57<14:00:25,  1.71it/s]
Train steps ... :  14%|█▍        | 13832/100000 [3:45:58<14:00:38,  1.71it/s]
Train steps ... :  14%|█▍        | 13833/100000 [3:45:58<14:00:16,  1.71it/s]
Train steps ... :  14%|█▍        | 13834/100000 [3:45:59<14:00:23,  1.71it/s]
Train steps ... :  14%|█▍        | 13835/100000 [3:45:59<14:02:51,  1.70it/s]
Train steps ... :  14%|█▍        | 13836/100000 [3:46:00<14:01:15,  1.71it/s]
Train steps ... :  14%|█▍        | 13837/100000 [3:46:01<14:01:37,  1.71it/s]
Train steps ... :  14%|█▍        | 13838/100000 [3:46:01<14:02:12,  1.71it/s]
Train steps ... :  14%|█▍        | 13839/100000 [3:46:02<14:01:27,  1.71it/s]
Train steps ... :  14%|█▍        | 13840/100000 [3:46:02<14:02:08,  1.71it/s]
Train steps ... :  14%|█▍        | 13841/100000 [3:46:03<14:01:03,  1.71it/s]
Train steps ... :  14%|█▍        | 13842/100000 [3:46:04<14:00:04,  1.71it/s]
Train steps ... :  14%|█▍        | 13843/100000 [3:46:04<14:04:59,  1.70it/s]
Train steps ... :  14%|█▍        | 13844/100000 [3:46:05<14:01:24,  1.71it/s]
Train steps ... :  14%|█▍        | 13845/100000 [3:46:05<14:00:48,  1.71it/s]
Train steps ... :  14%|█▍        | 13846/100000 [3:46:06<14:01:36,  1.71it/s]
Train steps ... :  14%|█▍        | 13847/100000 [3:46:07<14:02:56,  1.70it/s]
Train steps ... :  14%|█▍        | 13848/100000 [3:46:07<14:01:44,  1.71it/s]
Train steps ... :  14%|█▍        | 13849/100000 [3:46:08<14:02:47,  1.70it/s]
Train steps ... :  14%|█▍        | 13850/100000 [3:46:08<14:01:19,  1.71it/s]Step... (13850 / 100000 | Loss: 1.4945149421691895, Learning Rate: 8.658291457286433e-05)
+
                                                                             
Step... (13850 / 100000 | Loss: 0.9333401918411255, Learning Rate: 8.658291457286433e-05)
+
Train steps ... :  14%|█▍        | 13850/100000 [3:46:09<14:01:19,  1.71it/s]
Train steps ... :  14%|█▍        | 13851/100000 [3:46:09<14:01:58,  1.71it/s]
Train steps ... :  14%|█▍        | 13852/100000 [3:46:09<14:03:42,  1.70it/s]
Train steps ... :  14%|█▍        | 13853/100000 [3:46:10<14:01:48,  1.71it/s]
Train steps ... :  14%|█▍        | 13854/100000 [3:46:11<14:02:38,  1.70it/s]
Train steps ... :  14%|█▍        | 13855/100000 [3:46:11<14:01:25,  1.71it/s]
Train steps ... :  14%|█▍        | 13856/100000 [3:46:12<14:03:25,  1.70it/s]
Train steps ... :  14%|█▍        | 13857/100000 [3:46:12<14:02:00,  1.71it/s]
Train steps ... :  14%|█▍        | 13858/100000 [3:46:13<14:01:35,  1.71it/s]
Train steps ... :  14%|█▍        | 13859/100000 [3:46:14<14:02:08,  1.70it/s]
Train steps ... :  14%|█▍        | 13860/100000 [3:46:14<14:00:29,  1.71it/s]
Train steps ... :  14%|█▍        | 13861/100000 [3:46:15<14:02:23,  1.70it/s]
Train steps ... :  14%|█▍        | 13862/100000 [3:46:15<14:01:54,  1.71it/s]
Train steps ... :  14%|█▍        | 13863/100000 [3:46:16<14:00:55,  1.71it/s]
Train steps ... :  14%|█▍        | 13864/100000 [3:46:16<14:01:32,  1.71it/s]
Train steps ... :  14%|█▍        | 13865/100000 [3:46:17<14:00:34,  1.71it/s]
Train steps ... :  14%|█▍        | 13866/100000 [3:46:18<14:02:05,  1.70it/s]
Train steps ... :  14%|█▍        | 13867/100000 [3:46:18<14:00:25,  1.71it/s]
Train steps ... :  14%|█▍        | 13868/100000 [3:46:19<14:02:18,  1.70it/s]
Train steps ... :  14%|█▍        | 13869/100000 [3:46:19<14:00:02,  1.71it/s]
Train steps ... :  14%|█▍        | 13870/100000 [3:46:20<14:00:35,  1.71it/s]
Train steps ... :  14%|█▍        | 13871/100000 [3:46:21<14:01:24,  1.71it/s]
Train steps ... :  14%|█▍        | 13872/100000 [3:46:21<14:05:04,  1.70it/s]
Train steps ... :  14%|█▍        | 13873/100000 [3:46:22<14:01:26,  1.71it/s]
Train steps ... :  14%|█▍        | 13874/100000 [3:46:22<14:00:37,  1.71it/s]
Train steps ... :  14%|█▍        | 13875/100000 [3:46:23<14:02:39,  1.70it/s]Step... (13875 / 100000 | Loss: 1.098272442817688, Learning Rate: 8.655778894472362e-05)
+
                                                                             
Step... (13875 / 100000 | Loss: 1.0152275562286377, Learning Rate: 8.655778894472362e-05)
+
Train steps ... :  14%|█▍        | 13875/100000 [3:46:23<14:02:39,  1.70it/s]
Train steps ... :  14%|█▍        | 13876/100000 [3:46:24<14:02:50,  1.70it/s]
Train steps ... :  14%|█▍        | 13877/100000 [3:46:24<14:01:52,  1.70it/s]
Train steps ... :  14%|█▍        | 13878/100000 [3:46:25<14:03:48,  1.70it/s]
Train steps ... :  14%|█▍        | 13879/100000 [3:46:25<14:02:14,  1.70it/s]
Train steps ... :  14%|█▍        | 13880/100000 [3:46:26<14:01:42,  1.71it/s]
Train steps ... :  14%|█▍        | 13881/100000 [3:46:26<14:00:57,  1.71it/s]
Train steps ... :  14%|█▍        | 13882/100000 [3:46:27<14:01:22,  1.71it/s]
Train steps ... :  14%|█▍        | 13883/100000 [3:46:28<14:00:31,  1.71it/s]
Train steps ... :  14%|█▍        | 13884/100000 [3:46:28<14:01:15,  1.71it/s]
Train steps ... :  14%|█▍        | 13885/100000 [3:46:29<13:58:56,  1.71it/s]
Train steps ... :  14%|█▍        | 13886/100000 [3:46:29<13:59:40,  1.71it/s]
Train steps ... :  14%|█▍        | 13887/100000 [3:46:30<13:59:46,  1.71it/s]
Train steps ... :  14%|█▍        | 13888/100000 [3:46:31<14:01:07,  1.71it/s]
Train steps ... :  14%|█▍        | 13889/100000 [3:46:31<13:58:23,  1.71it/s]
Train steps ... :  14%|█▍        | 13890/100000 [3:46:32<13:59:20,  1.71it/s]
Train steps ... :  14%|█▍        | 13891/100000 [3:46:32<14:01:34,  1.71it/s]
Train steps ... :  14%|█▍        | 13892/100000 [3:46:33<13:59:48,  1.71it/s]
Train steps ... :  14%|█▍        | 13893/100000 [3:46:33<14:00:20,  1.71it/s]
Train steps ... :  14%|█▍        | 13894/100000 [3:46:34<13:59:39,  1.71it/s]
Train steps ... :  14%|█▍        | 13895/100000 [3:46:35<13:59:16,  1.71it/s]
Train steps ... :  14%|█▍        | 13896/100000 [3:46:35<13:59:43,  1.71it/s]
Train steps ... :  14%|█▍        | 13897/100000 [3:46:36<14:00:44,  1.71it/s]
Train steps ... :  14%|█▍        | 13898/100000 [3:46:36<14:00:49,  1.71it/s]
Train steps ... :  14%|█▍        | 13899/100000 [3:46:37<14:01:30,  1.71it/s]
Train steps ... :  14%|█▍        | 13900/100000 [3:46:38<14:02:18,  1.70it/s]Step... (13900 / 100000 | Loss: 1.5027050971984863, Learning Rate: 8.653266331658291e-05)
+
                                                                             
Step... (13900 / 100000 | Loss: 1.299736499786377, Learning Rate: 8.653266331658291e-05)
+
Train steps ... :  14%|█▍        | 13900/100000 [3:46:38<14:02:18,  1.70it/s]
Train steps ... :  14%|█▍        | 13901/100000 [3:46:38<14:06:04,  1.70it/s]
Train steps ... :  14%|█▍        | 13902/100000 [3:46:39<14:07:11,  1.69it/s]
Train steps ... :  14%|█▍        | 13903/100000 [3:46:39<14:06:49,  1.69it/s]
Train steps ... :  14%|█▍        | 13904/100000 [3:46:40<14:06:52,  1.69it/s]
Train steps ... :  14%|█▍        | 13905/100000 [3:46:41<14:06:52,  1.69it/s]
Train steps ... :  14%|█▍        | 13906/100000 [3:46:41<14:03:58,  1.70it/s]
Train steps ... :  14%|█▍        | 13907/100000 [3:46:42<14:02:45,  1.70it/s]
Train steps ... :  14%|█▍        | 13908/100000 [3:46:42<14:02:43,  1.70it/s]
Train steps ... :  14%|█▍        | 13909/100000 [3:46:43<14:04:41,  1.70it/s]
Train steps ... :  14%|█▍        | 13910/100000 [3:46:43<14:02:46,  1.70it/s]
Train steps ... :  14%|█▍        | 13911/100000 [3:46:44<14:06:19,  1.70it/s]
Train steps ... :  14%|█▍        | 13912/100000 [3:46:45<14:00:40,  1.71it/s]
Train steps ... :  14%|█▍        | 13913/100000 [3:46:45<14:03:08,  1.70it/s]
Train steps ... :  14%|█▍        | 13914/100000 [3:46:46<14:01:47,  1.70it/s]
Train steps ... :  14%|█▍        | 13915/100000 [3:46:46<14:01:51,  1.70it/s]
Train steps ... :  14%|█▍        | 13916/100000 [3:46:47<14:01:01,  1.71it/s]
Train steps ... :  14%|█▍        | 13917/100000 [3:46:48<14:00:02,  1.71it/s]
Train steps ... :  14%|█▍        | 13918/100000 [3:46:48<14:00:47,  1.71it/s]
Train steps ... :  14%|█▍        | 13919/100000 [3:46:49<14:00:51,  1.71it/s]
Train steps ... :  14%|█▍        | 13920/100000 [3:46:49<14:02:00,  1.70it/s]
Train steps ... :  14%|█▍        | 13921/100000 [3:46:50<14:01:12,  1.71it/s]
Train steps ... :  14%|█▍        | 13922/100000 [3:46:51<14:00:58,  1.71it/s]
Train steps ... :  14%|█▍        | 13923/100000 [3:46:51<14:01:23,  1.71it/s]
Train steps ... :  14%|█▍        | 13924/100000 [3:46:52<14:00:05,  1.71it/s]
Train steps ... :  14%|█▍        | 13925/100000 [3:46:52<14:00:18,  1.71it/s]Step... (13925 / 100000 | Loss: 0.9870256781578064, Learning Rate: 8.650753768844222e-05)
+
                                                                             
Step... (13925 / 100000 | Loss: 0.9806942939758301, Learning Rate: 8.650753768844222e-05)
+
Train steps ... :  14%|█▍        | 13925/100000 [3:46:53<14:00:18,  1.71it/s]
Train steps ... :  14%|█▍        | 13926/100000 [3:46:53<14:01:00,  1.71it/s]
Train steps ... :  14%|█▍        | 13927/100000 [3:46:53<14:00:06,  1.71it/s]
Train steps ... :  14%|█▍        | 13928/100000 [3:46:54<13:59:11,  1.71it/s]
Train steps ... :  14%|█▍        | 13929/100000 [3:46:55<14:01:28,  1.70it/s]
Train steps ... :  14%|█▍        | 13930/100000 [3:46:55<13:59:36,  1.71it/s]
Train steps ... :  14%|█▍        | 13931/100000 [3:46:56<14:02:04,  1.70it/s]
Train steps ... :  14%|█▍        | 13932/100000 [3:46:56<14:01:39,  1.70it/s]
Train steps ... :  14%|█▍        | 13933/100000 [3:46:57<14:00:51,  1.71it/s]
Train steps ... :  14%|█▍        | 13934/100000 [3:46:58<14:00:49,  1.71it/s]
Train steps ... :  14%|█▍        | 13935/100000 [3:46:58<13:59:52,  1.71it/s]
Train steps ... :  14%|█▍        | 13936/100000 [3:46:59<14:01:50,  1.70it/s]
Train steps ... :  14%|█▍        | 13937/100000 [3:46:59<13:59:23,  1.71it/s]
Train steps ... :  14%|█▍        | 13938/100000 [3:47:00<14:00:02,  1.71it/s]
Train steps ... :  14%|█▍        | 13939/100000 [3:47:00<14:00:22,  1.71it/s]
Train steps ... :  14%|█▍        | 13940/100000 [3:47:01<13:59:45,  1.71it/s]
Train steps ... :  14%|█▍        | 13941/100000 [3:47:02<14:00:34,  1.71it/s]
Train steps ... :  14%|█▍        | 13942/100000 [3:47:02<14:00:49,  1.71it/s]
Train steps ... :  14%|█▍        | 13943/100000 [3:47:03<14:00:29,  1.71it/s]
Train steps ... :  14%|█▍        | 13944/100000 [3:47:03<14:01:00,  1.71it/s]
Train steps ... :  14%|█▍        | 13945/100000 [3:47:04<14:01:44,  1.70it/s]
Train steps ... :  14%|█▍        | 13946/100000 [3:47:05<14:02:34,  1.70it/s]
Train steps ... :  14%|█▍        | 13947/100000 [3:47:05<14:01:49,  1.70it/s]
Train steps ... :  14%|█▍        | 13948/100000 [3:47:06<14:01:19,  1.70it/s]
Train steps ... :  14%|█▍        | 13949/100000 [3:47:06<14:00:38,  1.71it/s]
Train steps ... :  14%|█▍        | 13950/100000 [3:47:07<14:01:34,  1.70it/s]Step... (13950 / 100000 | Loss: 1.664117455482483, Learning Rate: 8.64824120603015e-05)
+
                                                                             
Step... (13950 / 100000 | Loss: 1.2166965007781982, Learning Rate: 8.64824120603015e-05)
+
Train steps ... :  14%|█▍        | 13950/100000 [3:47:07<14:01:34,  1.70it/s]
Train steps ... :  14%|█▍        | 13951/100000 [3:47:08<13:59:59,  1.71it/s]
Train steps ... :  14%|█▍        | 13952/100000 [3:47:08<14:01:54,  1.70it/s]
Train steps ... :  14%|█▍        | 13953/100000 [3:47:09<14:02:41,  1.70it/s]
Train steps ... :  14%|█▍        | 13954/100000 [3:47:09<14:02:27,  1.70it/s]
Train steps ... :  14%|█▍        | 13955/100000 [3:47:10<14:00:51,  1.71it/s]
Train steps ... :  14%|█▍        | 13956/100000 [3:47:10<14:00:18,  1.71it/s]
Train steps ... :  14%|█▍        | 13957/100000 [3:47:11<14:00:50,  1.71it/s]
Train steps ... :  14%|█▍        | 13958/100000 [3:47:12<14:03:04,  1.70it/s]
Train steps ... :  14%|█▍        | 13959/100000 [3:47:12<13:59:06,  1.71it/s]
Train steps ... :  14%|█▍        | 13960/100000 [3:47:13<13:59:23,  1.71it/s]
Train steps ... :  14%|█▍        | 13961/100000 [3:47:13<13:59:22,  1.71it/s]
Train steps ... :  14%|█▍        | 13962/100000 [3:47:14<13:59:37,  1.71it/s]
Train steps ... :  14%|█▍        | 13963/100000 [3:47:15<13:59:23,  1.71it/s]
Train steps ... :  14%|█▍        | 13964/100000 [3:47:15<14:01:35,  1.70it/s]
Train steps ... :  14%|█▍        | 13965/100000 [3:47:16<14:00:26,  1.71it/s]
Train steps ... :  14%|█▍        | 13966/100000 [3:47:16<13:59:26,  1.71it/s]
Train steps ... :  14%|█▍        | 13967/100000 [3:47:17<13:59:00,  1.71it/s]
Train steps ... :  14%|█▍        | 13968/100000 [3:47:17<13:58:49,  1.71it/s]
Train steps ... :  14%|█▍        | 13969/100000 [3:47:18<13:58:53,  1.71it/s]
Train steps ... :  14%|█▍        | 13970/100000 [3:47:19<13:58:43,  1.71it/s]
Train steps ... :  14%|█▍        | 13971/100000 [3:47:19<13:58:50,  1.71it/s]
Train steps ... :  14%|█▍        | 13972/100000 [3:47:20<14:00:26,  1.71it/s]
Train steps ... :  14%|█▍        | 13973/100000 [3:47:20<13:59:34,  1.71it/s]
Train steps ... :  14%|█▍        | 13974/100000 [3:47:21<13:59:21,  1.71it/s]
Train steps ... :  14%|█▍        | 13975/100000 [3:47:22<13:58:57,  1.71it/s]Step... (13975 / 100000 | Loss: 0.9343909025192261, Learning Rate: 8.645728643216082e-05)
+
                                                                             
Step... (13975 / 100000 | Loss: 1.1853022575378418, Learning Rate: 8.645728643216082e-05)
+
Train steps ... :  14%|█▍        | 13975/100000 [3:47:22<13:58:57,  1.71it/s]
Train steps ... :  14%|█▍        | 13976/100000 [3:47:22<14:00:41,  1.71it/s]
Train steps ... :  14%|█▍        | 13977/100000 [3:47:23<13:59:25,  1.71it/s]
Train steps ... :  14%|█▍        | 13978/100000 [3:47:23<13:59:29,  1.71it/s]
Train steps ... :  14%|█▍        | 13979/100000 [3:47:24<13:59:02,  1.71it/s]
Train steps ... :  14%|█▍        | 13980/100000 [3:47:24<13:58:39,  1.71it/s]
Train steps ... :  14%|█▍        | 13981/100000 [3:47:25<14:00:27,  1.71it/s]
Train steps ... :  14%|█▍        | 13982/100000 [3:47:26<13:58:27,  1.71it/s]
Train steps ... :  14%|█▍        | 13983/100000 [3:47:26<13:58:34,  1.71it/s]
Train steps ... :  14%|█▍        | 13984/100000 [3:47:27<13:59:28,  1.71it/s]
Train steps ... :  14%|█▍        | 13985/100000 [3:47:27<13:59:39,  1.71it/s]
Train steps ... :  14%|█▍        | 13986/100000 [3:47:28<13:59:34,  1.71it/s]
Train steps ... :  14%|█▍        | 13987/100000 [3:47:29<13:58:58,  1.71it/s]
Train steps ... :  14%|█▍        | 13988/100000 [3:47:29<14:00:54,  1.70it/s]
Train steps ... :  14%|█▍        | 13989/100000 [3:47:30<13:59:57,  1.71it/s]
Train steps ... :  14%|█▍        | 13990/100000 [3:47:30<13:59:38,  1.71it/s]
Train steps ... :  14%|█▍        | 13991/100000 [3:47:31<13:59:39,  1.71it/s]
Train steps ... :  14%|█▍        | 13992/100000 [3:47:32<14:03:10,  1.70it/s]
Train steps ... :  14%|█▍        | 13993/100000 [3:47:32<13:59:32,  1.71it/s]
Train steps ... :  14%|█▍        | 13994/100000 [3:47:33<14:04:33,  1.70it/s]
Train steps ... :  14%|█▍        | 13995/100000 [3:47:33<14:04:16,  1.70it/s]
Train steps ... :  14%|█▍        | 13996/100000 [3:47:34<14:00:32,  1.71it/s]
Train steps ... :  14%|█▍        | 13997/100000 [3:47:34<14:01:32,  1.70it/s]
Train steps ... :  14%|█▍        | 13998/100000 [3:47:35<14:02:26,  1.70it/s]
Train steps ... :  14%|█▍        | 13999/100000 [3:47:36<14:00:47,  1.70it/s]
Train steps ... :  14%|█▍        | 14000/100000 [3:47:36<14:00:49,  1.70it/s]Step... (14000 / 100000 | Loss: 1.22892427444458, Learning Rate: 8.64321608040201e-05)
+
                                                                             
Step... (14000 / 100000 | Loss: 1.066308617591858, Learning Rate: 8.64321608040201e-05)
+
Train steps ... :  14%|█▍        | 14000/100000 [3:47:37<14:00:49,  1.70it/s]
Train steps ... :  14%|█▍        | 14001/100000 [3:47:37<14:01:57,  1.70it/s]
Train steps ... :  14%|█▍        | 14002/100000 [3:47:37<14:01:09,  1.70it/s]
Train steps ... :  14%|█▍        | 14003/100000 [3:47:38<14:00:37,  1.71it/s]
Train steps ... :  14%|█▍        | 14004/100000 [3:47:39<14:00:17,  1.71it/s]
Train steps ... :  14%|█▍        | 14005/100000 [3:47:39<13:59:56,  1.71it/s]
Train steps ... :  14%|█▍        | 14006/100000 [3:47:40<13:59:59,  1.71it/s]
Train steps ... :  14%|█▍        | 14007/100000 [3:47:40<13:59:22,  1.71it/s]
Train steps ... :  14%|█▍        | 14008/100000 [3:47:41<14:01:24,  1.70it/s]
Train steps ... :  14%|█▍        | 14009/100000 [3:47:42<14:00:39,  1.70it/s]
Train steps ... :  14%|█▍        | 14010/100000 [3:47:42<13:59:42,  1.71it/s]
Train steps ... :  14%|█▍        | 14011/100000 [3:47:43<14:01:11,  1.70it/s]
Train steps ... :  14%|█▍        | 14012/100000 [3:47:43<14:01:30,  1.70it/s]
Train steps ... :  14%|█▍        | 14013/100000 [3:47:44<14:00:58,  1.70it/s]
Train steps ... :  14%|█▍        | 14014/100000 [3:47:44<14:00:37,  1.70it/s]
Train steps ... :  14%|█▍        | 14015/100000 [3:47:45<13:59:42,  1.71it/s]
Train steps ... :  14%|█▍        | 14016/100000 [3:47:46<13:58:00,  1.71it/s]
Train steps ... :  14%|█▍        | 14017/100000 [3:47:46<13:58:14,  1.71it/s]
Train steps ... :  14%|█▍        | 14018/100000 [3:47:47<14:00:00,  1.71it/s]
Train steps ... :  14%|█▍        | 14019/100000 [3:47:47<13:58:53,  1.71it/s]
Train steps ... :  14%|█▍        | 14020/100000 [3:47:48<13:59:43,  1.71it/s]
Train steps ... :  14%|█▍        | 14021/100000 [3:47:49<13:58:19,  1.71it/s]
Train steps ... :  14%|█▍        | 14022/100000 [3:47:49<13:59:22,  1.71it/s]
Train steps ... :  14%|█▍        | 14023/100000 [3:47:50<13:58:04,  1.71it/s]
Train steps ... :  14%|█▍        | 14024/100000 [3:47:50<13:58:19,  1.71it/s]
Train steps ... :  14%|█▍        | 14025/100000 [3:47:51<13:59:23,  1.71it/s]Step... (14025 / 100000 | Loss: 0.9388357996940613, Learning Rate: 8.640703517587941e-05)
+
                                                                             
Step... (14025 / 100000 | Loss: 1.071685791015625, Learning Rate: 8.640703517587941e-05)
+
Train steps ... :  14%|█▍        | 14025/100000 [3:47:51<13:59:23,  1.71it/s]
Train steps ... :  14%|█▍        | 14026/100000 [3:47:51<13:57:42,  1.71it/s]
Train steps ... :  14%|█▍        | 14027/100000 [3:47:52<14:01:09,  1.70it/s]
Train steps ... :  14%|█▍        | 14028/100000 [3:47:53<13:59:46,  1.71it/s]
Train steps ... :  14%|█▍        | 14029/100000 [3:47:53<13:59:18,  1.71it/s]
Train steps ... :  14%|█▍        | 14030/100000 [3:47:54<14:00:08,  1.71it/s]
Train steps ... :  14%|█▍        | 14031/100000 [3:47:54<14:00:53,  1.70it/s]
Train steps ... :  14%|█▍        | 14032/100000 [3:47:55<14:01:38,  1.70it/s]
Train steps ... :  14%|█▍        | 14033/100000 [3:47:56<14:01:10,  1.70it/s]
Train steps ... :  14%|█▍        | 14034/100000 [3:47:56<14:01:07,  1.70it/s]
Train steps ... :  14%|█▍        | 14035/100000 [3:47:57<13:59:17,  1.71it/s]
Train steps ... :  14%|█▍        | 14036/100000 [3:47:57<13:57:41,  1.71it/s]
Train steps ... :  14%|█▍        | 14037/100000 [3:47:58<14:01:15,  1.70it/s]
Train steps ... :  14%|█▍        | 14038/100000 [3:47:59<14:00:25,  1.70it/s]
Train steps ... :  14%|█▍        | 14039/100000 [3:47:59<13:59:39,  1.71it/s]
Train steps ... :  14%|█▍        | 14040/100000 [3:48:00<14:00:32,  1.70it/s]
Train steps ... :  14%|█▍        | 14041/100000 [3:48:00<13:59:12,  1.71it/s]
Train steps ... :  14%|█▍        | 14042/100000 [3:48:01<14:00:30,  1.70it/s]
Train steps ... :  14%|█▍        | 14043/100000 [3:48:01<14:01:40,  1.70it/s]
Train steps ... :  14%|█▍        | 14044/100000 [3:48:02<13:58:38,  1.71it/s]
Train steps ... :  14%|█▍        | 14045/100000 [3:48:03<14:01:02,  1.70it/s]
Train steps ... :  14%|█▍        | 14046/100000 [3:48:03<13:59:52,  1.71it/s]
Train steps ... :  14%|█▍        | 14047/100000 [3:48:04<13:59:24,  1.71it/s]
Train steps ... :  14%|█▍        | 14048/100000 [3:48:04<13:59:43,  1.71it/s]
Train steps ... :  14%|█▍        | 14049/100000 [3:48:05<13:58:25,  1.71it/s]
Train steps ... :  14%|█▍        | 14050/100000 [3:48:06<14:02:29,  1.70it/s]Step... (14050 / 100000 | Loss: 0.812820553779602, Learning Rate: 8.638190954773869e-05)
+
                                                                             
Step... (14050 / 100000 | Loss: 1.3981760740280151, Learning Rate: 8.638190954773869e-05)
+
Train steps ... :  14%|█▍        | 14050/100000 [3:48:06<14:02:29,  1.70it/s]
Train steps ... :  14%|█▍        | 14051/100000 [3:48:06<14:00:49,  1.70it/s]
Train steps ... :  14%|█▍        | 14052/100000 [3:48:07<14:00:49,  1.70it/s]
Train steps ... :  14%|█▍        | 14053/100000 [3:48:07<14:00:11,  1.70it/s]
Train steps ... :  14%|█▍        | 14054/100000 [3:48:08<14:00:13,  1.70it/s]
Train steps ... :  14%|█▍        | 14055/100000 [3:48:08<13:59:11,  1.71it/s]
Train steps ... :  14%|█▍        | 14056/100000 [3:48:09<13:58:38,  1.71it/s]
Train steps ... :  14%|█▍        | 14057/100000 [3:48:10<13:58:01,  1.71it/s]
Train steps ... :  14%|█▍        | 14058/100000 [3:48:10<13:57:56,  1.71it/s]
Train steps ... :  14%|█▍        | 14059/100000 [3:48:11<13:59:45,  1.71it/s]
Train steps ... :  14%|█▍        | 14060/100000 [3:48:11<13:59:57,  1.71it/s]
Train steps ... :  14%|█▍        | 14061/100000 [3:48:12<13:59:22,  1.71it/s]
Train steps ... :  14%|█▍        | 14062/100000 [3:48:13<13:58:29,  1.71it/s]
Train steps ... :  14%|█▍        | 14063/100000 [3:48:13<13:58:07,  1.71it/s]
Train steps ... :  14%|█▍        | 14064/100000 [3:48:14<14:00:11,  1.70it/s]
Train steps ... :  14%|█▍        | 14065/100000 [3:48:14<13:58:39,  1.71it/s]
Train steps ... :  14%|█▍        | 14066/100000 [3:48:15<13:58:19,  1.71it/s]
Train steps ... :  14%|█▍        | 14067/100000 [3:48:15<13:58:36,  1.71it/s]
Train steps ... :  14%|█▍        | 14068/100000 [3:48:16<13:58:13,  1.71it/s]
Train steps ... :  14%|█▍        | 14069/100000 [3:48:17<13:59:41,  1.71it/s]
Train steps ... :  14%|█▍        | 14070/100000 [3:48:17<13:57:31,  1.71it/s]
Train steps ... :  14%|█▍        | 14071/100000 [3:48:18<14:00:30,  1.70it/s]
Train steps ... :  14%|█▍        | 14072/100000 [3:48:18<14:00:06,  1.70it/s]
Train steps ... :  14%|█▍        | 14073/100000 [3:48:19<13:59:54,  1.71it/s]
Train steps ... :  14%|█▍        | 14074/100000 [3:48:20<14:00:06,  1.70it/s]
Train steps ... :  14%|█▍        | 14075/100000 [3:48:20<14:00:33,  1.70it/s]Step... (14075 / 100000 | Loss: 1.3179066181182861, Learning Rate: 8.635678391959799e-05)
+
                                                                             
Step... (14075 / 100000 | Loss: 1.075836181640625, Learning Rate: 8.635678391959799e-05)
+
Train steps ... :  14%|█▍        | 14075/100000 [3:48:21<14:00:33,  1.70it/s]
Train steps ... :  14%|█▍        | 14076/100000 [3:48:21<14:01:44,  1.70it/s]
Train steps ... :  14%|█▍        | 14077/100000 [3:48:21<14:00:29,  1.70it/s]
Train steps ... :  14%|█▍        | 14078/100000 [3:48:22<13:59:49,  1.71it/s]
Train steps ... :  14%|█▍        | 14079/100000 [3:48:23<14:01:24,  1.70it/s]
Train steps ... :  14%|█▍        | 14080/100000 [3:48:23<13:58:04,  1.71it/s]
Train steps ... :  14%|█▍        | 14081/100000 [3:48:24<13:57:37,  1.71it/s]
Train steps ... :  14%|█▍        | 14082/100000 [3:48:24<13:58:09,  1.71it/s]
Train steps ... :  14%|█▍        | 14083/100000 [3:48:25<13:58:19,  1.71it/s]
Train steps ... :  14%|█▍        | 14084/100000 [3:48:25<13:58:33,  1.71it/s]
Train steps ... :  14%|█▍        | 14085/100000 [3:48:26<13:59:05,  1.71it/s]
Train steps ... :  14%|█▍        | 14086/100000 [3:48:27<13:59:57,  1.70it/s]
Train steps ... :  14%|█▍        | 14087/100000 [3:48:27<13:59:56,  1.70it/s]
Train steps ... :  14%|█▍        | 14088/100000 [3:48:28<13:59:11,  1.71it/s]
Train steps ... :  14%|█▍        | 14089/100000 [3:48:28<13:59:05,  1.71it/s]
Train steps ... :  14%|█▍        | 14090/100000 [3:48:29<13:58:59,  1.71it/s]
Train steps ... :  14%|█▍        | 14091/100000 [3:48:30<13:57:17,  1.71it/s]
Train steps ... :  14%|█▍        | 14092/100000 [3:48:30<13:57:08,  1.71it/s]
Train steps ... :  14%|█▍        | 14093/100000 [3:48:31<13:58:11,  1.71it/s]
Train steps ... :  14%|█▍        | 14094/100000 [3:48:31<14:01:33,  1.70it/s]
Train steps ... :  14%|█▍        | 14095/100000 [3:48:32<13:58:44,  1.71it/s]
Train steps ... :  14%|█▍        | 14096/100000 [3:48:32<14:00:27,  1.70it/s]
Train steps ... :  14%|█▍        | 14097/100000 [3:48:33<13:59:06,  1.71it/s]
Train steps ... :  14%|█▍        | 14098/100000 [3:48:34<13:58:28,  1.71it/s]
Train steps ... :  14%|█▍        | 14099/100000 [3:48:34<13:59:37,  1.71it/s]
Train steps ... :  14%|█▍        | 14100/100000 [3:48:35<14:01:37,  1.70it/s]Step... (14100 / 100000 | Loss: 1.3651015758514404, Learning Rate: 8.63316582914573e-05)
+
                                                                             
Step... (14100 / 100000 | Loss: 2.129868268966675, Learning Rate: 8.63316582914573e-05)
+
Train steps ... :  14%|█▍        | 14100/100000 [3:48:35<14:01:37,  1.70it/s]
Train steps ... :  14%|█▍        | 14101/100000 [3:48:35<13:59:27,  1.71it/s]
Train steps ... :  14%|█▍        | 14102/100000 [3:48:36<13:58:08,  1.71it/s]
Train steps ... :  14%|█▍        | 14103/100000 [3:48:37<13:57:38,  1.71it/s]
Train steps ... :  14%|█▍        | 14104/100000 [3:48:37<13:57:16,  1.71it/s]
Train steps ... :  14%|█▍        | 14105/100000 [3:48:38<13:57:16,  1.71it/s]
Train steps ... :  14%|█▍        | 14106/100000 [3:48:38<13:58:07,  1.71it/s]
Train steps ... :  14%|█▍        | 14107/100000 [3:48:39<13:56:22,  1.71it/s]
Train steps ... :  14%|█▍        | 14108/100000 [3:48:40<13:56:35,  1.71it/s]
Train steps ... :  14%|█▍        | 14109/100000 [3:48:40<13:58:17,  1.71it/s]
Train steps ... :  14%|█▍        | 14110/100000 [3:48:41<13:55:43,  1.71it/s]
Train steps ... :  14%|█▍        | 14111/100000 [3:48:41<13:56:27,  1.71it/s]
Train steps ... :  14%|█▍        | 14112/100000 [3:48:42<13:56:30,  1.71it/s]
Train steps ... :  14%|█▍        | 14113/100000 [3:48:42<13:57:19,  1.71it/s]
Train steps ... :  14%|█▍        | 14114/100000 [3:48:43<13:57:02,  1.71it/s]
Train steps ... :  14%|█▍        | 14115/100000 [3:48:44<13:58:58,  1.71it/s]
Train steps ... :  14%|█▍        | 14116/100000 [3:48:44<13:58:51,  1.71it/s]
Train steps ... :  14%|█▍        | 14117/100000 [3:48:45<13:58:09,  1.71it/s]
Train steps ... :  14%|█▍        | 14118/100000 [3:48:45<13:59:40,  1.70it/s]
Train steps ... :  14%|█▍        | 14119/100000 [3:48:46<13:59:09,  1.71it/s]
Train steps ... :  14%|█▍        | 14120/100000 [3:48:47<13:58:05,  1.71it/s]
Train steps ... :  14%|█▍        | 14121/100000 [3:48:47<14:00:22,  1.70it/s]
Train steps ... :  14%|█▍        | 14122/100000 [3:48:48<13:58:53,  1.71it/s]
Train steps ... :  14%|█▍        | 14123/100000 [3:48:48<13:57:08,  1.71it/s]
Train steps ... :  14%|█▍        | 14124/100000 [3:48:49<13:58:42,  1.71it/s]
Train steps ... :  14%|█▍        | 14125/100000 [3:48:49<13:58:17,  1.71it/s]Step... (14125 / 100000 | Loss: 1.368659496307373, Learning Rate: 8.630653266331658e-05)
+
                                                                             
Step... (14125 / 100000 | Loss: 1.2136824131011963, Learning Rate: 8.630653266331658e-05)
+
Train steps ... :  14%|█▍        | 14125/100000 [3:48:50<13:58:17,  1.71it/s]
Train steps ... :  14%|█▍        | 14126/100000 [3:48:50<13:58:51,  1.71it/s]
Train steps ... :  14%|█▍        | 14127/100000 [3:48:51<13:59:36,  1.70it/s]
Train steps ... :  14%|█▍        | 14128/100000 [3:48:51<13:58:17,  1.71it/s]
Train steps ... :  14%|█▍        | 14129/100000 [3:48:52<14:02:19,  1.70it/s]
Train steps ... :  14%|█▍        | 14130/100000 [3:48:52<14:02:59,  1.70it/s]
Train steps ... :  14%|█▍        | 14131/100000 [3:48:53<14:01:26,  1.70it/s]
Train steps ... :  14%|█▍        | 14132/100000 [3:48:54<13:59:54,  1.70it/s]
Train steps ... :  14%|█▍        | 14133/100000 [3:48:54<13:58:31,  1.71it/s]
Train steps ... :  14%|█▍        | 14134/100000 [3:48:55<13:57:20,  1.71it/s]
Train steps ... :  14%|█▍        | 14135/100000 [3:48:55<13:57:20,  1.71it/s]
Train steps ... :  14%|█▍        | 14136/100000 [3:48:56<13:57:57,  1.71it/s]
Train steps ... :  14%|█▍        | 14137/100000 [3:48:57<13:57:55,  1.71it/s]
Train steps ... :  14%|█▍        | 14138/100000 [3:48:57<13:58:32,  1.71it/s]
Train steps ... :  14%|█▍        | 14139/100000 [3:48:58<14:00:08,  1.70it/s]
Train steps ... :  14%|█▍        | 14140/100000 [3:48:58<13:57:53,  1.71it/s]
Train steps ... :  14%|█▍        | 14141/100000 [3:48:59<13:58:05,  1.71it/s]
Train steps ... :  14%|█▍        | 14142/100000 [3:48:59<13:57:14,  1.71it/s]
Train steps ... :  14%|█▍        | 14143/100000 [3:49:00<14:00:59,  1.70it/s]
Train steps ... :  14%|█▍        | 14144/100000 [3:49:01<14:04:38,  1.69it/s]
Train steps ... :  14%|█▍        | 14145/100000 [3:49:01<13:59:19,  1.70it/s]
Train steps ... :  14%|█▍        | 14146/100000 [3:49:02<13:58:45,  1.71it/s]
Train steps ... :  14%|█▍        | 14147/100000 [3:49:02<13:58:52,  1.71it/s]
Train steps ... :  14%|█▍        | 14148/100000 [3:49:03<13:57:58,  1.71it/s]
Train steps ... :  14%|█▍        | 14149/100000 [3:49:04<13:57:16,  1.71it/s]
Train steps ... :  14%|█▍        | 14150/100000 [3:49:04<13:57:22,  1.71it/s]Step... (14150 / 100000 | Loss: 0.9498798847198486, Learning Rate: 8.628140703517589e-05)
+
                                                                             
Step... (14150 / 100000 | Loss: 1.0251039266586304, Learning Rate: 8.628140703517589e-05)
+
Train steps ... :  14%|█▍        | 14150/100000 [3:49:04<13:57:22,  1.71it/s]
Train steps ... :  14%|█▍        | 14151/100000 [3:49:05<13:57:56,  1.71it/s]
Train steps ... :  14%|█▍        | 14152/100000 [3:49:05<13:59:42,  1.70it/s]
Train steps ... :  14%|█▍        | 14153/100000 [3:49:06<13:58:46,  1.71it/s]
Train steps ... :  14%|█▍        | 14154/100000 [3:49:06<13:56:31,  1.71it/s]
Train steps ... :  14%|█▍        | 14155/100000 [3:49:07<13:57:22,  1.71it/s]
Train steps ... :  14%|█▍        | 14156/100000 [3:49:08<13:58:39,  1.71it/s]
Train steps ... :  14%|█▍        | 14157/100000 [3:49:08<13:59:38,  1.70it/s]
Train steps ... :  14%|█▍        | 14158/100000 [3:49:09<13:58:23,  1.71it/s]
Train steps ... :  14%|█▍        | 14159/100000 [3:49:09<13:58:03,  1.71it/s]
Train steps ... :  14%|█▍        | 14160/100000 [3:49:10<13:58:03,  1.71it/s]
Train steps ... :  14%|█▍        | 14161/100000 [3:49:11<13:58:02,  1.71it/s]
Train steps ... :  14%|█▍        | 14162/100000 [3:49:11<13:59:38,  1.70it/s]
Train steps ... :  14%|█▍        | 14163/100000 [3:49:12<14:02:41,  1.70it/s]
Train steps ... :  14%|█▍        | 14164/100000 [3:49:12<13:58:23,  1.71it/s]
Train steps ... :  14%|█▍        | 14165/100000 [3:49:13<14:01:19,  1.70it/s]
Train steps ... :  14%|█▍        | 14166/100000 [3:49:14<14:01:15,  1.70it/s]
Train steps ... :  14%|█▍        | 14167/100000 [3:49:14<14:04:17,  1.69it/s]
Train steps ... :  14%|█▍        | 14168/100000 [3:49:15<13:59:32,  1.70it/s]
Train steps ... :  14%|█▍        | 14169/100000 [3:49:15<14:03:24,  1.70it/s]
Train steps ... :  14%|█▍        | 14170/100000 [3:49:16<14:01:27,  1.70it/s]
Train steps ... :  14%|█▍        | 14171/100000 [3:49:16<14:08:55,  1.69it/s]
Train steps ... :  14%|█▍        | 14172/100000 [3:49:17<14:05:55,  1.69it/s]
Train steps ... :  14%|█▍        | 14173/100000 [3:49:18<14:03:52,  1.70it/s]
Train steps ... :  14%|█▍        | 14174/100000 [3:49:18<14:03:09,  1.70it/s]
Train steps ... :  14%|█▍        | 14175/100000 [3:49:19<14:02:45,  1.70it/s]Step... (14175 / 100000 | Loss: 1.0986292362213135, Learning Rate: 8.625628140703518e-05)
+
                                                                             
Step... (14175 / 100000 | Loss: 1.2349598407745361, Learning Rate: 8.625628140703518e-05)
+
Train steps ... :  14%|█▍        | 14175/100000 [3:49:19<14:02:45,  1.70it/s]
Train steps ... :  14%|█▍        | 14176/100000 [3:49:19<14:01:52,  1.70it/s]
Train steps ... :  14%|█▍        | 14177/100000 [3:49:20<13:59:32,  1.70it/s]
Train steps ... :  14%|█▍        | 14178/100000 [3:49:21<14:00:53,  1.70it/s]
Train steps ... :  14%|█▍        | 14179/100000 [3:49:21<13:59:11,  1.70it/s]
Train steps ... :  14%|█▍        | 14180/100000 [3:49:22<13:57:54,  1.71it/s]
Train steps ... :  14%|█▍        | 14181/100000 [3:49:22<13:56:48,  1.71it/s]
Train steps ... :  14%|█▍        | 14182/100000 [3:49:23<13:57:57,  1.71it/s]
Train steps ... :  14%|█▍        | 14183/100000 [3:49:24<13:57:12,  1.71it/s]
Train steps ... :  14%|█▍        | 14184/100000 [3:49:24<13:58:47,  1.71it/s]
Train steps ... :  14%|█▍        | 14185/100000 [3:49:25<13:56:46,  1.71it/s]
Train steps ... :  14%|█▍        | 14186/100000 [3:49:25<13:57:09,  1.71it/s]
Train steps ... :  14%|█▍        | 14187/100000 [3:49:26<13:59:12,  1.70it/s]
Train steps ... :  14%|█▍        | 14188/100000 [3:49:26<13:58:29,  1.71it/s]
Train steps ... :  14%|█▍        | 14189/100000 [3:49:27<13:57:18,  1.71it/s]
Train steps ... :  14%|█▍        | 14190/100000 [3:49:28<13:57:36,  1.71it/s]
Train steps ... :  14%|█▍        | 14191/100000 [3:49:28<13:59:03,  1.70it/s]
Train steps ... :  14%|█▍        | 14192/100000 [3:49:29<13:58:41,  1.71it/s]
Train steps ... :  14%|█▍        | 14193/100000 [3:49:29<13:58:28,  1.71it/s]
Train steps ... :  14%|█▍        | 14194/100000 [3:49:30<14:00:49,  1.70it/s]
Train steps ... :  14%|█▍        | 14195/100000 [3:49:31<13:59:09,  1.70it/s]
Train steps ... :  14%|█▍        | 14196/100000 [3:49:31<13:57:59,  1.71it/s]
Train steps ... :  14%|█▍        | 14197/100000 [3:49:32<13:57:32,  1.71it/s]
Train steps ... :  14%|█▍        | 14198/100000 [3:49:32<13:56:56,  1.71it/s]
Train steps ... :  14%|█▍        | 14199/100000 [3:49:33<13:56:38,  1.71it/s]
Train steps ... :  14%|█▍        | 14200/100000 [3:49:33<13:57:10,  1.71it/s]Step... (14200 / 100000 | Loss: 1.1613622903823853, Learning Rate: 8.623115577889449e-05)
+
                                                                             
Step... (14200 / 100000 | Loss: 1.1173670291900635, Learning Rate: 8.623115577889449e-05)
+
Train steps ... :  14%|█▍        | 14200/100000 [3:49:34<13:57:10,  1.71it/s]
Train steps ... :  14%|█▍        | 14201/100000 [3:49:34<13:57:30,  1.71it/s]
Train steps ... :  14%|█▍        | 14202/100000 [3:49:35<13:57:36,  1.71it/s]
Train steps ... :  14%|█▍        | 14203/100000 [3:49:35<13:57:27,  1.71it/s]
Train steps ... :  14%|█▍        | 14204/100000 [3:49:36<13:58:54,  1.70it/s]
Train steps ... :  14%|█▍        | 14205/100000 [3:49:36<13:57:33,  1.71it/s]
Train steps ... :  14%|█▍        | 14206/100000 [3:49:37<13:56:57,  1.71it/s]
Train steps ... :  14%|█▍        | 14207/100000 [3:49:38<13:56:46,  1.71it/s]
Train steps ... :  14%|█▍        | 14208/100000 [3:49:38<13:55:51,  1.71it/s]
Train steps ... :  14%|█▍        | 14209/100000 [3:49:39<13:56:28,  1.71it/s]
Train steps ... :  14%|█▍        | 14210/100000 [3:49:39<13:57:09,  1.71it/s]
Train steps ... :  14%|█▍        | 14211/100000 [3:49:40<13:57:14,  1.71it/s]
Train steps ... :  14%|█▍        | 14212/100000 [3:49:41<13:56:30,  1.71it/s]
Train steps ... :  14%|█▍        | 14213/100000 [3:49:41<13:56:06,  1.71it/s]
Train steps ... :  14%|█▍        | 14214/100000 [3:49:42<13:56:51,  1.71it/s]
Train steps ... :  14%|█▍        | 14215/100000 [3:49:42<13:55:46,  1.71it/s]
Train steps ... :  14%|█▍        | 14216/100000 [3:49:43<13:58:46,  1.70it/s]
Train steps ... :  14%|█▍        | 14217/100000 [3:49:43<13:55:39,  1.71it/s]
Train steps ... :  14%|█▍        | 14218/100000 [3:49:44<13:55:12,  1.71it/s]
Train steps ... :  14%|█▍        | 14219/100000 [3:49:45<13:56:00,  1.71it/s]
Train steps ... :  14%|█▍        | 14220/100000 [3:49:45<13:57:47,  1.71it/s]
Train steps ... :  14%|█▍        | 14221/100000 [3:49:46<13:56:37,  1.71it/s]
Train steps ... :  14%|█▍        | 14222/100000 [3:49:46<13:57:31,  1.71it/s]
Train steps ... :  14%|█▍        | 14223/100000 [3:49:47<13:59:33,  1.70it/s]
Train steps ... :  14%|█▍        | 14224/100000 [3:49:48<13:59:39,  1.70it/s]
Train steps ... :  14%|█▍        | 14225/100000 [3:49:48<13:59:02,  1.70it/s]Step... (14225 / 100000 | Loss: 1.0962198972702026, Learning Rate: 8.620603015075377e-05)
+
                                                                             
Step... (14225 / 100000 | Loss: 1.714069128036499, Learning Rate: 8.620603015075377e-05)
+
Train steps ... :  14%|█▍        | 14225/100000 [3:49:48<13:59:02,  1.70it/s]
Train steps ... :  14%|█▍        | 14226/100000 [3:49:49<13:59:49,  1.70it/s]
Train steps ... :  14%|█▍        | 14227/100000 [3:49:49<13:58:08,  1.71it/s]
Train steps ... :  14%|█▍        | 14228/100000 [3:49:50<13:59:04,  1.70it/s]
Train steps ... :  14%|█▍        | 14229/100000 [3:49:50<13:59:35,  1.70it/s]
Train steps ... :  14%|█▍        | 14230/100000 [3:49:51<13:59:36,  1.70it/s]
Train steps ... :  14%|█▍        | 14231/100000 [3:49:52<13:57:51,  1.71it/s]
Train steps ... :  14%|█▍        | 14232/100000 [3:49:52<13:55:04,  1.71it/s]
Train steps ... :  14%|█▍        | 14233/100000 [3:49:53<13:57:07,  1.71it/s]
Train steps ... :  14%|█▍        | 14234/100000 [3:49:53<13:56:52,  1.71it/s]
Train steps ... :  14%|█▍        | 14235/100000 [3:49:54<13:56:21,  1.71it/s]
Train steps ... :  14%|█▍        | 14236/100000 [3:49:55<13:56:00,  1.71it/s]
Train steps ... :  14%|█▍        | 14237/100000 [3:49:55<13:55:26,  1.71it/s]
Train steps ... :  14%|█▍        | 14238/100000 [3:49:56<13:55:53,  1.71it/s]
Train steps ... :  14%|█▍        | 14239/100000 [3:49:56<13:58:34,  1.70it/s]
Train steps ... :  14%|█▍        | 14240/100000 [3:49:57<13:56:55,  1.71it/s]
Train steps ... :  14%|█▍        | 14241/100000 [3:49:57<13:55:51,  1.71it/s]
Train steps ... :  14%|█▍        | 14242/100000 [3:49:58<13:57:38,  1.71it/s]
Train steps ... :  14%|█▍        | 14243/100000 [3:49:59<13:57:15,  1.71it/s]
Train steps ... :  14%|█▍        | 14244/100000 [3:49:59<13:56:40,  1.71it/s]
Train steps ... :  14%|█▍        | 14245/100000 [3:50:00<13:57:24,  1.71it/s]
Train steps ... :  14%|█▍        | 14246/100000 [3:50:00<13:57:39,  1.71it/s]
Train steps ... :  14%|█▍        | 14247/100000 [3:50:01<13:57:42,  1.71it/s]
Train steps ... :  14%|█▍        | 14248/100000 [3:50:02<14:00:52,  1.70it/s]
Train steps ... :  14%|█▍        | 14249/100000 [3:50:02<13:58:20,  1.70it/s]
Train steps ... :  14%|█▍        | 14250/100000 [3:50:03<13:59:56,  1.70it/s]Step... (14250 / 100000 | Loss: 1.8362877368927002, Learning Rate: 8.618090452261306e-05)
+
                                                                             
Step... (14250 / 100000 | Loss: 1.4341135025024414, Learning Rate: 8.618090452261306e-05)
+
Train steps ... :  14%|█▍        | 14250/100000 [3:50:03<13:59:56,  1.70it/s]
Train steps ... :  14%|█▍        | 14251/100000 [3:50:03<13:58:28,  1.70it/s]
Train steps ... :  14%|█▍        | 14252/100000 [3:50:04<13:57:31,  1.71it/s]
Train steps ... :  14%|█▍        | 14253/100000 [3:50:05<13:57:47,  1.71it/s]
Train steps ... :  14%|█▍        | 14254/100000 [3:50:05<13:56:58,  1.71it/s]
Train steps ... :  14%|█▍        | 14255/100000 [3:50:06<13:55:38,  1.71it/s]
Train steps ... :  14%|█▍        | 14256/100000 [3:50:06<13:56:07,  1.71it/s]
Train steps ... :  14%|█▍        | 14257/100000 [3:50:07<13:54:50,  1.71it/s]
Train steps ... :  14%|█▍        | 14258/100000 [3:50:07<13:56:00,  1.71it/s]
Train steps ... :  14%|█▍        | 14259/100000 [3:50:08<13:56:15,  1.71it/s]
Train steps ... :  14%|█▍        | 14260/100000 [3:50:09<13:55:45,  1.71it/s]
Train steps ... :  14%|█▍        | 14261/100000 [3:50:09<13:56:35,  1.71it/s]
Train steps ... :  14%|█▍        | 14262/100000 [3:50:10<13:59:13,  1.70it/s]
Train steps ... :  14%|█▍        | 14263/100000 [3:50:10<13:59:01,  1.70it/s]
Train steps ... :  14%|█▍        | 14264/100000 [3:50:11<14:00:02,  1.70it/s]
Train steps ... :  14%|█▍        | 14265/100000 [3:50:12<14:01:57,  1.70it/s]
Train steps ... :  14%|█▍        | 14266/100000 [3:50:12<13:59:16,  1.70it/s]
Train steps ... :  14%|█▍        | 14267/100000 [3:50:13<13:59:28,  1.70it/s]
Train steps ... :  14%|█▍        | 14268/100000 [3:50:13<13:59:24,  1.70it/s]
Train steps ... :  14%|█▍        | 14269/100000 [3:50:14<13:59:55,  1.70it/s]
Train steps ... :  14%|█▍        | 14270/100000 [3:50:15<13:58:45,  1.70it/s]
Train steps ... :  14%|█▍        | 14271/100000 [3:50:15<13:58:35,  1.70it/s]
Train steps ... :  14%|█▍        | 14272/100000 [3:50:16<13:58:25,  1.70it/s]
Train steps ... :  14%|█▍        | 14273/100000 [3:50:16<13:58:43,  1.70it/s]
Train steps ... :  14%|█▍        | 14274/100000 [3:50:17<13:57:56,  1.71it/s]
Train steps ... :  14%|█▍        | 14275/100000 [3:50:17<13:57:35,  1.71it/s]Step... (14275 / 100000 | Loss: 1.054133653640747, Learning Rate: 8.615577889447236e-05)
+
                                                                             
Step... (14275 / 100000 | Loss: 1.262890338897705, Learning Rate: 8.615577889447236e-05)
+
Train steps ... :  14%|█▍        | 14275/100000 [3:50:18<13:57:35,  1.71it/s]
Train steps ... :  14%|█▍        | 14276/100000 [3:50:18<13:57:00,  1.71it/s]
Train steps ... :  14%|█▍        | 14277/100000 [3:50:19<13:57:22,  1.71it/s]
Train steps ... :  14%|█▍        | 14278/100000 [3:50:19<13:56:52,  1.71it/s]
Train steps ... :  14%|█▍        | 14279/100000 [3:50:20<13:56:05,  1.71it/s]
Train steps ... :  14%|█▍        | 14280/100000 [3:50:20<13:58:16,  1.70it/s]
Train steps ... :  14%|█▍        | 14281/100000 [3:50:21<13:57:14,  1.71it/s]
Train steps ... :  14%|█▍        | 14282/100000 [3:50:22<13:57:06,  1.71it/s]
Train steps ... :  14%|█▍        | 14283/100000 [3:50:22<13:56:58,  1.71it/s]
Train steps ... :  14%|█▍        | 14284/100000 [3:50:23<13:56:54,  1.71it/s]
Train steps ... :  14%|█▍        | 14285/100000 [3:50:23<13:59:06,  1.70it/s]
Train steps ... :  14%|█▍        | 14286/100000 [3:50:24<13:55:27,  1.71it/s]
Train steps ... :  14%|█▍        | 14287/100000 [3:50:24<13:56:48,  1.71it/s]
Train steps ... :  14%|█▍        | 14288/100000 [3:50:25<13:55:44,  1.71it/s]
Train steps ... :  14%|█▍        | 14289/100000 [3:50:26<13:57:13,  1.71it/s]
Train steps ... :  14%|█▍        | 14290/100000 [3:50:26<13:57:52,  1.70it/s]
Train steps ... :  14%|█▍        | 14291/100000 [3:50:27<13:56:26,  1.71it/s]
Train steps ... :  14%|█▍        | 14292/100000 [3:50:27<13:56:54,  1.71it/s]
Train steps ... :  14%|█▍        | 14293/100000 [3:50:28<13:57:57,  1.70it/s]
Train steps ... :  14%|█▍        | 14294/100000 [3:50:29<13:56:09,  1.71it/s]
Train steps ... :  14%|█▍        | 14295/100000 [3:50:29<13:57:15,  1.71it/s]
Train steps ... :  14%|█▍        | 14296/100000 [3:50:30<13:59:48,  1.70it/s]
Train steps ... :  14%|█▍        | 14297/100000 [3:50:30<13:59:51,  1.70it/s]
Train steps ... :  14%|█▍        | 14298/100000 [3:50:31<13:56:58,  1.71it/s]
Train steps ... :  14%|█▍        | 14299/100000 [3:50:32<13:58:55,  1.70it/s]
Train steps ... :  14%|█▍        | 14300/100000 [3:50:32<13:57:51,  1.70it/s]Step... (14300 / 100000 | Loss: 0.9453551769256592, Learning Rate: 8.613065326633166e-05)
+
                                                                             
Step... (14300 / 100000 | Loss: 0.8249126672744751, Learning Rate: 8.613065326633166e-05)
+
Train steps ... :  14%|█▍        | 14300/100000 [3:50:32<13:57:51,  1.70it/s]
Train steps ... :  14%|█▍        | 14301/100000 [3:50:33<14:02:36,  1.70it/s]
Train steps ... :  14%|█▍        | 14302/100000 [3:50:33<13:59:22,  1.70it/s]
Train steps ... :  14%|█▍        | 14303/100000 [3:50:34<14:00:18,  1.70it/s]
Train steps ... :  14%|█▍        | 14304/100000 [3:50:34<14:02:26,  1.70it/s]
Train steps ... :  14%|█▍        | 14305/100000 [3:50:35<14:00:16,  1.70it/s]
Train steps ... :  14%|█▍        | 14306/100000 [3:50:36<14:02:36,  1.70it/s]
Train steps ... :  14%|█▍        | 14307/100000 [3:50:36<13:58:31,  1.70it/s]
Train steps ... :  14%|█▍        | 14308/100000 [3:50:37<13:57:37,  1.71it/s]
Train steps ... :  14%|█▍        | 14309/100000 [3:50:37<13:58:27,  1.70it/s]
Train steps ... :  14%|█▍        | 14310/100000 [3:50:38<13:58:27,  1.70it/s]
Train steps ... :  14%|█▍        | 14311/100000 [3:50:39<13:56:43,  1.71it/s]
Train steps ... :  14%|█▍        | 14312/100000 [3:50:39<13:57:57,  1.70it/s]
Train steps ... :  14%|█▍        | 14313/100000 [3:50:40<13:58:48,  1.70it/s]
Train steps ... :  14%|█▍        | 14314/100000 [3:50:40<13:57:43,  1.70it/s]
Train steps ... :  14%|█▍        | 14315/100000 [3:50:41<13:56:46,  1.71it/s]
Train steps ... :  14%|█▍        | 14316/100000 [3:50:41<13:58:32,  1.70it/s]
Train steps ... :  14%|█▍        | 14317/100000 [3:50:42<13:55:12,  1.71it/s]
Train steps ... :  14%|█▍        | 14318/100000 [3:50:43<13:58:51,  1.70it/s]
Train steps ... :  14%|█▍        | 14319/100000 [3:50:43<13:58:15,  1.70it/s]
Train steps ... :  14%|█▍        | 14320/100000 [3:50:44<13:54:58,  1.71it/s]
Train steps ... :  14%|█▍        | 14321/100000 [3:50:44<13:56:02,  1.71it/s]
Train steps ... :  14%|█▍        | 14322/100000 [3:50:45<13:55:20,  1.71it/s]
Train steps ... :  14%|█▍        | 14323/100000 [3:50:46<13:55:31,  1.71it/s]
Train steps ... :  14%|█▍        | 14324/100000 [3:50:46<13:58:51,  1.70it/s]
Train steps ... :  14%|█▍        | 14325/100000 [3:50:47<13:58:10,  1.70it/s]Step... (14325 / 100000 | Loss: 1.5869107246398926, Learning Rate: 8.610552763819097e-05)
+
                                                                             
Step... (14325 / 100000 | Loss: 1.5293943881988525, Learning Rate: 8.610552763819097e-05)
+
Train steps ... :  14%|█▍        | 14325/100000 [3:50:47<13:58:10,  1.70it/s]
Train steps ... :  14%|█▍        | 14326/100000 [3:50:47<13:57:43,  1.70it/s]
Train steps ... :  14%|█▍        | 14327/100000 [3:50:48<13:55:52,  1.71it/s]
Train steps ... :  14%|█▍        | 14328/100000 [3:50:49<13:56:05,  1.71it/s]
Train steps ... :  14%|█▍        | 14329/100000 [3:50:49<13:56:20,  1.71it/s]
Train steps ... :  14%|█▍        | 14330/100000 [3:50:50<13:55:34,  1.71it/s]
Train steps ... :  14%|█▍        | 14331/100000 [3:50:50<13:55:59,  1.71it/s]
Train steps ... :  14%|█▍        | 14332/100000 [3:50:51<13:58:27,  1.70it/s]
Train steps ... :  14%|█▍        | 14333/100000 [3:50:51<13:58:33,  1.70it/s]
Train steps ... :  14%|█▍        | 14334/100000 [3:50:52<13:56:29,  1.71it/s]
Train steps ... :  14%|█▍        | 14335/100000 [3:50:53<13:57:35,  1.70it/s]
Train steps ... :  14%|█▍        | 14336/100000 [3:50:53<13:55:12,  1.71it/s]
Train steps ... :  14%|█▍        | 14337/100000 [3:50:54<13:54:25,  1.71it/s]
Train steps ... :  14%|█▍        | 14338/100000 [3:50:54<13:54:47,  1.71it/s]
Train steps ... :  14%|█▍        | 14339/100000 [3:50:55<13:54:12,  1.71it/s]
Train steps ... :  14%|█▍        | 14340/100000 [3:50:56<13:54:59,  1.71it/s]
Train steps ... :  14%|█▍        | 14341/100000 [3:50:56<13:57:13,  1.71it/s]
Train steps ... :  14%|█▍        | 14342/100000 [3:50:57<13:55:29,  1.71it/s]
Train steps ... :  14%|█▍        | 14343/100000 [3:50:57<13:54:20,  1.71it/s]
Train steps ... :  14%|█▍        | 14344/100000 [3:50:58<13:54:17,  1.71it/s]
Train steps ... :  14%|█▍        | 14345/100000 [3:50:58<13:55:24,  1.71it/s]
Train steps ... :  14%|█▍        | 14346/100000 [3:50:59<13:56:41,  1.71it/s]
Train steps ... :  14%|█▍        | 14347/100000 [3:51:00<13:57:39,  1.70it/s]
Train steps ... :  14%|█▍        | 14348/100000 [3:51:00<13:55:56,  1.71it/s]
Train steps ... :  14%|█▍        | 14349/100000 [3:51:01<13:55:23,  1.71it/s]
Train steps ... :  14%|█▍        | 14350/100000 [3:51:01<13:56:12,  1.71it/s]Step... (14350 / 100000 | Loss: 1.0872259140014648, Learning Rate: 8.608040201005025e-05)
+
                                                                             
Step... (14350 / 100000 | Loss: 1.0711643695831299, Learning Rate: 8.608040201005025e-05)
+
Train steps ... :  14%|█▍        | 14350/100000 [3:51:02<13:56:12,  1.71it/s]
Train steps ... :  14%|█▍        | 14351/100000 [3:51:02<13:56:00,  1.71it/s]
Train steps ... :  14%|█▍        | 14352/100000 [3:51:03<13:56:24,  1.71it/s]
Train steps ... :  14%|█▍        | 14353/100000 [3:51:03<13:55:55,  1.71it/s]
Train steps ... :  14%|█▍        | 14354/100000 [3:51:04<13:56:46,  1.71it/s]
Train steps ... :  14%|█▍        | 14355/100000 [3:51:04<13:55:43,  1.71it/s]
Train steps ... :  14%|█▍        | 14356/100000 [3:51:05<13:55:24,  1.71it/s]
Train steps ... :  14%|█▍        | 14357/100000 [3:51:06<13:55:54,  1.71it/s]
Train steps ... :  14%|█▍        | 14358/100000 [3:51:06<13:56:17,  1.71it/s]
Train steps ... :  14%|█▍        | 14359/100000 [3:51:07<13:55:33,  1.71it/s]
Train steps ... :  14%|█▍        | 14360/100000 [3:51:07<13:55:15,  1.71it/s]
Train steps ... :  14%|█▍        | 14361/100000 [3:51:08<13:56:57,  1.71it/s]
Train steps ... :  14%|█▍        | 14362/100000 [3:51:08<13:56:58,  1.71it/s]
Train steps ... :  14%|█▍        | 14363/100000 [3:51:09<13:56:26,  1.71it/s]
Train steps ... :  14%|█▍        | 14364/100000 [3:51:10<13:58:00,  1.70it/s]
Train steps ... :  14%|█▍        | 14365/100000 [3:51:10<13:58:12,  1.70it/s]
Train steps ... :  14%|█▍        | 14366/100000 [3:51:11<13:57:39,  1.70it/s]
Train steps ... :  14%|█▍        | 14367/100000 [3:51:11<13:57:52,  1.70it/s]
Train steps ... :  14%|█▍        | 14368/100000 [3:51:12<13:57:26,  1.70it/s]
Train steps ... :  14%|█▍        | 14369/100000 [3:51:13<13:57:04,  1.70it/s]
Train steps ... :  14%|█▍        | 14370/100000 [3:51:13<13:56:35,  1.71it/s]
Train steps ... :  14%|█▍        | 14371/100000 [3:51:14<13:55:32,  1.71it/s]
Train steps ... :  14%|█▍        | 14372/100000 [3:51:14<13:55:46,  1.71it/s]
Train steps ... :  14%|█▍        | 14373/100000 [3:51:15<13:55:53,  1.71it/s]
Train steps ... :  14%|█▍        | 14374/100000 [3:51:15<13:54:49,  1.71it/s]
Train steps ... :  14%|█▍        | 14375/100000 [3:51:16<13:55:16,  1.71it/s]Step... (14375 / 100000 | Loss: 1.1624255180358887, Learning Rate: 8.605527638190956e-05)
+
                                                                             
Step... (14375 / 100000 | Loss: 1.4845325946807861, Learning Rate: 8.605527638190956e-05)
+
Train steps ... :  14%|█▍        | 14375/100000 [3:51:16<13:55:16,  1.71it/s]
Train steps ... :  14%|█▍        | 14376/100000 [3:51:17<13:56:21,  1.71it/s]
Train steps ... :  14%|█▍        | 14377/100000 [3:51:17<13:56:19,  1.71it/s]
Train steps ... :  14%|█▍        | 14378/100000 [3:51:18<13:57:28,  1.70it/s]
Train steps ... :  14%|█▍        | 14379/100000 [3:51:18<13:54:29,  1.71it/s]
Train steps ... :  14%|█▍        | 14380/100000 [3:51:19<13:55:31,  1.71it/s]
Train steps ... :  14%|█▍        | 14381/100000 [3:51:20<13:56:32,  1.71it/s]
Train steps ... :  14%|█▍        | 14382/100000 [3:51:20<13:56:02,  1.71it/s]
Train steps ... :  14%|█▍        | 14383/100000 [3:51:21<13:55:56,  1.71it/s]
Train steps ... :  14%|█▍        | 14384/100000 [3:51:21<13:59:44,  1.70it/s]
Train steps ... :  14%|█▍        | 14385/100000 [3:51:22<13:57:14,  1.70it/s]
Train steps ... :  14%|█▍        | 14386/100000 [3:51:23<13:57:06,  1.70it/s]
Train steps ... :  14%|█▍        | 14387/100000 [3:51:23<13:55:44,  1.71it/s]
Train steps ... :  14%|█▍        | 14388/100000 [3:51:24<13:56:48,  1.71it/s]
Train steps ... :  14%|█▍        | 14389/100000 [3:51:24<13:56:09,  1.71it/s]
Train steps ... :  14%|█▍        | 14390/100000 [3:51:25<13:56:58,  1.70it/s]
Train steps ... :  14%|█▍        | 14391/100000 [3:51:25<13:55:09,  1.71it/s]
Train steps ... :  14%|█▍        | 14392/100000 [3:51:26<13:55:33,  1.71it/s]
Train steps ... :  14%|█▍        | 14393/100000 [3:51:27<13:56:28,  1.71it/s]
Train steps ... :  14%|█▍        | 14394/100000 [3:51:27<13:54:18,  1.71it/s]
Train steps ... :  14%|█▍        | 14395/100000 [3:51:28<13:55:30,  1.71it/s]
Train steps ... :  14%|█▍        | 14396/100000 [3:51:28<13:57:34,  1.70it/s]
Train steps ... :  14%|█▍        | 14397/100000 [3:51:29<13:58:14,  1.70it/s]
Train steps ... :  14%|█▍        | 14398/100000 [3:51:30<13:57:16,  1.70it/s]
Train steps ... :  14%|█▍        | 14399/100000 [3:51:30<13:59:15,  1.70it/s]
Train steps ... :  14%|█▍        | 14400/100000 [3:51:31<13:59:21,  1.70it/s]Step... (14400 / 100000 | Loss: 0.8966996073722839, Learning Rate: 8.603015075376884e-05)
+
                                                                             
Step... (14400 / 100000 | Loss: 1.595535397529602, Learning Rate: 8.603015075376884e-05)
+
Train steps ... :  14%|█▍        | 14400/100000 [3:51:31<13:59:21,  1.70it/s]
Train steps ... :  14%|█▍        | 14401/100000 [3:51:31<13:59:31,  1.70it/s]
Train steps ... :  14%|█▍        | 14402/100000 [3:51:32<13:56:23,  1.71it/s]
Train steps ... :  14%|█▍        | 14403/100000 [3:51:32<13:57:32,  1.70it/s]
Train steps ... :  14%|█▍        | 14404/100000 [3:51:33<13:55:50,  1.71it/s]
Train steps ... :  14%|█▍        | 14405/100000 [3:51:34<13:55:02,  1.71it/s]
Train steps ... :  14%|█▍        | 14406/100000 [3:51:34<13:54:31,  1.71it/s]
Train steps ... :  14%|█▍        | 14407/100000 [3:51:35<13:55:15,  1.71it/s]
Train steps ... :  14%|█▍        | 14408/100000 [3:51:35<13:54:42,  1.71it/s]
Train steps ... :  14%|█▍        | 14409/100000 [3:51:36<13:56:26,  1.71it/s]
Train steps ... :  14%|█▍        | 14410/100000 [3:51:37<13:54:48,  1.71it/s]
Train steps ... :  14%|█▍        | 14411/100000 [3:51:37<13:54:23,  1.71it/s]
Train steps ... :  14%|█▍        | 14412/100000 [3:51:38<13:56:05,  1.71it/s]
Train steps ... :  14%|█▍        | 14413/100000 [3:51:38<13:55:49,  1.71it/s]
Train steps ... :  14%|█▍        | 14414/100000 [3:51:39<13:56:15,  1.71it/s]
Train steps ... :  14%|█▍        | 14415/100000 [3:51:40<13:55:47,  1.71it/s]
Train steps ... :  14%|█▍        | 14416/100000 [3:51:40<13:56:51,  1.70it/s]
Train steps ... :  14%|█▍        | 14417/100000 [3:51:41<13:54:08,  1.71it/s]
Train steps ... :  14%|█▍        | 14418/100000 [3:51:41<13:55:00,  1.71it/s]
Train steps ... :  14%|█▍        | 14419/100000 [3:51:42<13:55:22,  1.71it/s]
Train steps ... :  14%|█▍        | 14420/100000 [3:51:42<13:55:38,  1.71it/s]
Train steps ... :  14%|█▍        | 14421/100000 [3:51:43<13:55:49,  1.71it/s]
Train steps ... :  14%|█▍        | 14422/100000 [3:51:44<13:55:50,  1.71it/s]
Train steps ... :  14%|█▍        | 14423/100000 [3:51:44<13:56:19,  1.71it/s]
Train steps ... :  14%|█▍        | 14424/100000 [3:51:45<13:56:51,  1.70it/s]
Train steps ... :  14%|█▍        | 14425/100000 [3:51:45<13:56:15,  1.71it/s]Step... (14425 / 100000 | Loss: 1.323866844177246, Learning Rate: 8.600502512562814e-05)
+
                                                                             
Step... (14425 / 100000 | Loss: 1.1540021896362305, Learning Rate: 8.600502512562814e-05)
+
Train steps ... :  14%|█▍        | 14425/100000 [3:51:46<13:56:15,  1.71it/s]
Train steps ... :  14%|█▍        | 14426/100000 [3:51:46<13:58:10,  1.70it/s]
Train steps ... :  14%|█▍        | 14427/100000 [3:51:47<13:55:51,  1.71it/s]
Train steps ... :  14%|█▍        | 14428/100000 [3:51:47<13:56:58,  1.70it/s]
Train steps ... :  14%|█▍        | 14429/100000 [3:51:48<13:57:26,  1.70it/s]
Train steps ... :  14%|█▍        | 14430/100000 [3:51:48<13:59:11,  1.70it/s]
Train steps ... :  14%|█▍        | 14431/100000 [3:51:49<13:57:36,  1.70it/s]
Train steps ... :  14%|█▍        | 14432/100000 [3:51:49<13:58:43,  1.70it/s]
Train steps ... :  14%|█▍        | 14433/100000 [3:51:50<13:56:32,  1.70it/s]
Train steps ... :  14%|█▍        | 14434/100000 [3:51:51<13:55:57,  1.71it/s]
Train steps ... :  14%|█▍        | 14435/100000 [3:51:51<13:56:08,  1.71it/s]
Train steps ... :  14%|█▍        | 14436/100000 [3:51:52<13:57:20,  1.70it/s]
Train steps ... :  14%|█▍        | 14437/100000 [3:51:52<13:57:05,  1.70it/s]
Train steps ... :  14%|█▍        | 14438/100000 [3:51:53<13:56:14,  1.71it/s]
Train steps ... :  14%|█▍        | 14439/100000 [3:51:54<13:54:39,  1.71it/s]
Train steps ... :  14%|█▍        | 14440/100000 [3:51:54<13:55:30,  1.71it/s]
Train steps ... :  14%|█▍        | 14441/100000 [3:51:55<13:56:46,  1.70it/s]
Train steps ... :  14%|█▍        | 14442/100000 [3:51:55<13:55:46,  1.71it/s]
Train steps ... :  14%|█▍        | 14443/100000 [3:51:56<13:55:05,  1.71it/s]
Train steps ... :  14%|█▍        | 14444/100000 [3:51:57<13:57:33,  1.70it/s]
Train steps ... :  14%|█▍        | 14445/100000 [3:51:57<13:56:26,  1.70it/s]
Train steps ... :  14%|█▍        | 14446/100000 [3:51:58<13:57:04,  1.70it/s]
Train steps ... :  14%|█▍        | 14447/100000 [3:51:58<13:56:07,  1.71it/s]
Train steps ... :  14%|█▍        | 14448/100000 [3:51:59<13:58:08,  1.70it/s]
Train steps ... :  14%|█▍        | 14449/100000 [3:51:59<13:54:11,  1.71it/s]
Train steps ... :  14%|█▍        | 14450/100000 [3:52:00<13:57:29,  1.70it/s]Step... (14450 / 100000 | Loss: 1.0382996797561646, Learning Rate: 8.597989949748744e-05)
+
                                                                             
Step... (14450 / 100000 | Loss: 1.564024567604065, Learning Rate: 8.597989949748744e-05)
+
Train steps ... :  14%|█▍        | 14450/100000 [3:52:00<13:57:29,  1.70it/s]
Train steps ... :  14%|█▍        | 14451/100000 [3:52:01<13:56:17,  1.70it/s]
Train steps ... :  14%|█▍        | 14452/100000 [3:52:01<13:54:06,  1.71it/s]
Train steps ... :  14%|█▍        | 14453/100000 [3:52:02<13:55:03,  1.71it/s]
Train steps ... :  14%|█▍        | 14454/100000 [3:52:02<13:56:18,  1.70it/s]
Train steps ... :  14%|█▍        | 14455/100000 [3:52:03<13:55:34,  1.71it/s]
Train steps ... :  14%|█▍        | 14456/100000 [3:52:04<13:55:44,  1.71it/s]
Train steps ... :  14%|█▍        | 14457/100000 [3:52:04<13:54:39,  1.71it/s]
Train steps ... :  14%|█▍        | 14458/100000 [3:52:05<13:54:53,  1.71it/s]
Train steps ... :  14%|█▍        | 14459/100000 [3:52:05<13:55:02,  1.71it/s]
Train steps ... :  14%|█▍        | 14460/100000 [3:52:06<13:56:45,  1.70it/s]
Train steps ... :  14%|█▍        | 14461/100000 [3:52:06<13:54:07,  1.71it/s]
Train steps ... :  14%|█▍        | 14462/100000 [3:52:07<13:56:38,  1.70it/s]
Train steps ... :  14%|█▍        | 14463/100000 [3:52:08<13:54:21,  1.71it/s]
Train steps ... :  14%|█▍        | 14464/100000 [3:52:08<13:55:24,  1.71it/s]
Train steps ... :  14%|█▍        | 14465/100000 [3:52:09<13:56:36,  1.70it/s]
Train steps ... :  14%|█▍        | 14466/100000 [3:52:09<13:55:05,  1.71it/s]
Train steps ... :  14%|█▍        | 14467/100000 [3:52:10<13:55:48,  1.71it/s]
Train steps ... :  14%|█▍        | 14468/100000 [3:52:11<13:54:47,  1.71it/s]
Train steps ... :  14%|█▍        | 14469/100000 [3:52:11<13:55:00,  1.71it/s]
Train steps ... :  14%|█▍        | 14470/100000 [3:52:12<13:57:02,  1.70it/s]
Train steps ... :  14%|█▍        | 14471/100000 [3:52:12<13:54:58,  1.71it/s]
Train steps ... :  14%|█▍        | 14472/100000 [3:52:13<13:54:35,  1.71it/s]
Train steps ... :  14%|█▍        | 14473/100000 [3:52:14<13:54:51,  1.71it/s]
Train steps ... :  14%|█▍        | 14474/100000 [3:52:14<13:56:05,  1.70it/s]
Train steps ... :  14%|█▍        | 14475/100000 [3:52:15<13:55:29,  1.71it/s]Step... (14475 / 100000 | Loss: 0.8735706210136414, Learning Rate: 8.595477386934673e-05)
+
                                                                             
Step... (14475 / 100000 | Loss: 1.0183377265930176, Learning Rate: 8.595477386934673e-05)
+
Train steps ... :  14%|█▍        | 14475/100000 [3:52:15<13:55:29,  1.71it/s]
Train steps ... :  14%|█▍        | 14476/100000 [3:52:15<13:58:27,  1.70it/s]
Train steps ... :  14%|█▍        | 14477/100000 [3:52:16<13:57:03,  1.70it/s]
Train steps ... :  14%|█▍        | 14478/100000 [3:52:16<13:56:44,  1.70it/s]
Train steps ... :  14%|█▍        | 14479/100000 [3:52:17<13:55:26,  1.71it/s]
Train steps ... :  14%|█▍        | 14480/100000 [3:52:18<13:55:28,  1.71it/s]
Train steps ... :  14%|█▍        | 14481/100000 [3:52:18<13:54:38,  1.71it/s]
Train steps ... :  14%|█▍        | 14482/100000 [3:52:19<13:55:11,  1.71it/s]
Train steps ... :  14%|█▍        | 14483/100000 [3:52:19<13:56:36,  1.70it/s]
Train steps ... :  14%|█▍        | 14484/100000 [3:52:20<13:55:10,  1.71it/s]
Train steps ... :  14%|█▍        | 14485/100000 [3:52:21<13:54:28,  1.71it/s]
Train steps ... :  14%|█▍        | 14486/100000 [3:52:21<13:53:27,  1.71it/s]
Train steps ... :  14%|█▍        | 14487/100000 [3:52:22<13:53:32,  1.71it/s]
Train steps ... :  14%|█▍        | 14488/100000 [3:52:22<13:57:00,  1.70it/s]
Train steps ... :  14%|█▍        | 14489/100000 [3:52:23<13:52:58,  1.71it/s]
Train steps ... :  14%|█▍        | 14490/100000 [3:52:23<13:52:50,  1.71it/s]
Train steps ... :  14%|█▍        | 14491/100000 [3:52:24<13:55:06,  1.71it/s]
Train steps ... :  14%|█▍        | 14492/100000 [3:52:25<13:56:18,  1.70it/s]
Train steps ... :  14%|█▍        | 14493/100000 [3:52:25<13:55:17,  1.71it/s]
Train steps ... :  14%|█▍        | 14494/100000 [3:52:26<13:55:05,  1.71it/s]
Train steps ... :  14%|█▍        | 14495/100000 [3:52:26<13:57:39,  1.70it/s]
Train steps ... :  14%|█▍        | 14496/100000 [3:52:27<13:58:29,  1.70it/s]
Train steps ... :  14%|█▍        | 14497/100000 [3:52:28<13:55:28,  1.71it/s]
Train steps ... :  14%|█▍        | 14498/100000 [3:52:28<13:54:27,  1.71it/s]
Train steps ... :  14%|█▍        | 14499/100000 [3:52:29<13:56:09,  1.70it/s]
Train steps ... :  14%|█▍        | 14500/100000 [3:52:29<13:56:30,  1.70it/s]Step... (14500 / 100000 | Loss: 0.8114151954650879, Learning Rate: 8.592964824120603e-05)
+
                                                                             
Step... (14500 / 100000 | Loss: 1.0917596817016602, Learning Rate: 8.592964824120603e-05)
+
Train steps ... :  14%|█▍        | 14500/100000 [3:52:30<13:56:30,  1.70it/s]
Train steps ... :  15%|█▍        | 14501/100000 [3:52:30<13:54:34,  1.71it/s]
Train steps ... :  15%|█▍        | 14502/100000 [3:52:31<13:55:09,  1.71it/s]
Train steps ... :  15%|█▍        | 14503/100000 [3:52:31<13:56:05,  1.70it/s]
Train steps ... :  15%|█▍        | 14504/100000 [3:52:32<13:57:17,  1.70it/s]
Train steps ... :  15%|█▍        | 14505/100000 [3:52:32<13:56:41,  1.70it/s]
Train steps ... :  15%|█▍        | 14506/100000 [3:52:33<13:56:13,  1.70it/s]
Train steps ... :  15%|█▍        | 14507/100000 [3:52:33<13:55:43,  1.70it/s]
Train steps ... :  15%|█▍        | 14508/100000 [3:52:34<13:54:21,  1.71it/s]
Train steps ... :  15%|█▍        | 14509/100000 [3:52:35<13:57:46,  1.70it/s]
Train steps ... :  15%|█▍        | 14510/100000 [3:52:35<13:56:08,  1.70it/s]
Train steps ... :  15%|█▍        | 14511/100000 [3:52:36<13:54:42,  1.71it/s]
Train steps ... :  15%|█▍        | 14512/100000 [3:52:36<13:53:17,  1.71it/s]
Train steps ... :  15%|█▍        | 14513/100000 [3:52:37<13:54:19,  1.71it/s]
Train steps ... :  15%|█▍        | 14514/100000 [3:52:38<13:54:03,  1.71it/s]
Train steps ... :  15%|█▍        | 14515/100000 [3:52:38<13:54:07,  1.71it/s]
Train steps ... :  15%|█▍        | 14516/100000 [3:52:39<13:54:26,  1.71it/s]
Train steps ... :  15%|█▍        | 14517/100000 [3:52:39<13:54:32,  1.71it/s]
Train steps ... :  15%|█▍        | 14518/100000 [3:52:40<13:53:33,  1.71it/s]
Train steps ... :  15%|█▍        | 14519/100000 [3:52:40<13:54:21,  1.71it/s]
Train steps ... :  15%|█▍        | 14520/100000 [3:52:41<13:53:35,  1.71it/s]
Train steps ... :  15%|█▍        | 14521/100000 [3:52:42<13:53:04,  1.71it/s]
Train steps ... :  15%|█▍        | 14522/100000 [3:52:42<13:52:38,  1.71it/s]
Train steps ... :  15%|█▍        | 14523/100000 [3:52:43<13:51:56,  1.71it/s]
Train steps ... :  15%|█▍        | 14524/100000 [3:52:43<13:51:33,  1.71it/s]
Train steps ... :  15%|█▍        | 14525/100000 [3:52:44<13:52:41,  1.71it/s]Step... (14525 / 100000 | Loss: 1.1333690881729126, Learning Rate: 8.590452261306533e-05)
+
                                                                             
Step... (14525 / 100000 | Loss: 1.2360689640045166, Learning Rate: 8.590452261306533e-05)
+
Train steps ... :  15%|█▍        | 14525/100000 [3:52:44<13:52:41,  1.71it/s]
Train steps ... :  15%|█▍        | 14526/100000 [3:52:45<13:53:53,  1.71it/s]
Train steps ... :  15%|█▍        | 14527/100000 [3:52:45<13:53:51,  1.71it/s]
Train steps ... :  15%|█▍        | 14528/100000 [3:52:46<13:53:25,  1.71it/s]
Train steps ... :  15%|█▍        | 14529/100000 [3:52:46<13:57:30,  1.70it/s]
Train steps ... :  15%|█▍        | 14530/100000 [3:52:47<13:56:18,  1.70it/s]
Train steps ... :  15%|█▍        | 14531/100000 [3:52:47<13:53:48,  1.71it/s]
Train steps ... :  15%|█▍        | 14532/100000 [3:52:48<13:54:24,  1.71it/s]
Train steps ... :  15%|█▍        | 14533/100000 [3:52:49<13:53:55,  1.71it/s]
Train steps ... :  15%|█▍        | 14534/100000 [3:52:49<13:55:26,  1.70it/s]
Train steps ... :  15%|█▍        | 14535/100000 [3:52:50<13:53:55,  1.71it/s]
Train steps ... :  15%|█▍        | 14536/100000 [3:52:50<13:55:57,  1.70it/s]
Train steps ... :  15%|█▍        | 14537/100000 [3:52:51<13:56:32,  1.70it/s]
Train steps ... :  15%|█▍        | 14538/100000 [3:52:52<13:59:10,  1.70it/s]
Train steps ... :  15%|█▍        | 14539/100000 [3:52:52<13:55:45,  1.70it/s]
Train steps ... :  15%|█▍        | 14540/100000 [3:52:53<13:59:44,  1.70it/s]
Train steps ... :  15%|█▍        | 14541/100000 [3:52:53<13:57:52,  1.70it/s]
Train steps ... :  15%|█▍        | 14542/100000 [3:52:54<13:58:04,  1.70it/s]
Train steps ... :  15%|█▍        | 14543/100000 [3:52:55<14:00:30,  1.69it/s]
Train steps ... :  15%|█▍        | 14544/100000 [3:52:55<13:57:32,  1.70it/s]
Train steps ... :  15%|█▍        | 14545/100000 [3:52:56<13:56:02,  1.70it/s]
Train steps ... :  15%|█▍        | 14546/100000 [3:52:56<13:55:11,  1.71it/s]
Train steps ... :  15%|█▍        | 14547/100000 [3:52:57<13:53:50,  1.71it/s]
Train steps ... :  15%|█▍        | 14548/100000 [3:52:57<13:54:10,  1.71it/s]
Train steps ... :  15%|█▍        | 14549/100000 [3:52:58<13:54:53,  1.71it/s]
Train steps ... :  15%|█▍        | 14550/100000 [3:52:59<13:54:44,  1.71it/s]Step... (14550 / 100000 | Loss: 0.913322925567627, Learning Rate: 8.587939698492464e-05)
+
                                                                             
Step... (14550 / 100000 | Loss: 1.1495106220245361, Learning Rate: 8.587939698492464e-05)
+
Train steps ... :  15%|█▍        | 14550/100000 [3:52:59<13:54:44,  1.71it/s]
Train steps ... :  15%|█▍        | 14551/100000 [3:52:59<13:54:20,  1.71it/s]
Train steps ... :  15%|█▍        | 14552/100000 [3:53:00<13:54:04,  1.71it/s]
Train steps ... :  15%|█▍        | 14553/100000 [3:53:00<13:54:18,  1.71it/s]
Train steps ... :  15%|█▍        | 14554/100000 [3:53:01<13:54:12,  1.71it/s]
Train steps ... :  15%|█▍        | 14555/100000 [3:53:02<13:53:54,  1.71it/s]
Train steps ... :  15%|█▍        | 14556/100000 [3:53:02<13:53:30,  1.71it/s]
Train steps ... :  15%|█▍        | 14557/100000 [3:53:03<13:53:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14558/100000 [3:53:03<13:54:16,  1.71it/s]
Train steps ... :  15%|█▍        | 14559/100000 [3:53:04<13:53:55,  1.71it/s]
Train steps ... :  15%|█▍        | 14560/100000 [3:53:05<13:53:40,  1.71it/s]
Train steps ... :  15%|█▍        | 14561/100000 [3:53:05<13:54:31,  1.71it/s]
Train steps ... :  15%|█▍        | 14562/100000 [3:53:06<13:59:07,  1.70it/s]
Train steps ... :  15%|█▍        | 14563/100000 [3:53:06<13:56:33,  1.70it/s]
Train steps ... :  15%|█▍        | 14564/100000 [3:53:07<13:56:46,  1.70it/s]
Train steps ... :  15%|█▍        | 14565/100000 [3:53:07<13:56:13,  1.70it/s]
Train steps ... :  15%|█▍        | 14566/100000 [3:53:08<13:55:52,  1.70it/s]
Train steps ... :  15%|█▍        | 14567/100000 [3:53:09<13:55:20,  1.70it/s]
Train steps ... :  15%|█▍        | 14568/100000 [3:53:09<13:56:21,  1.70it/s]
Train steps ... :  15%|█▍        | 14569/100000 [3:53:10<13:57:35,  1.70it/s]
Train steps ... :  15%|█▍        | 14570/100000 [3:53:10<13:57:02,  1.70it/s]
Train steps ... :  15%|█▍        | 14571/100000 [3:53:11<13:59:32,  1.70it/s]
Train steps ... :  15%|█▍        | 14572/100000 [3:53:12<13:56:26,  1.70it/s]
Train steps ... :  15%|█▍        | 14573/100000 [3:53:12<13:55:05,  1.70it/s]
Train steps ... :  15%|█▍        | 14574/100000 [3:53:13<13:53:52,  1.71it/s]
Train steps ... :  15%|█▍        | 14575/100000 [3:53:13<13:52:26,  1.71it/s]Step... (14575 / 100000 | Loss: 1.2319786548614502, Learning Rate: 8.585427135678392e-05)
+
                                                                             
Step... (14575 / 100000 | Loss: 1.1696655750274658, Learning Rate: 8.585427135678392e-05)
+
Train steps ... :  15%|█▍        | 14575/100000 [3:53:14<13:52:26,  1.71it/s]
Train steps ... :  15%|█▍        | 14576/100000 [3:53:14<13:53:10,  1.71it/s]
Train steps ... :  15%|█▍        | 14577/100000 [3:53:14<13:53:04,  1.71it/s]
Train steps ... :  15%|█▍        | 14578/100000 [3:53:15<13:53:46,  1.71it/s]
Train steps ... :  15%|█▍        | 14579/100000 [3:53:16<13:56:21,  1.70it/s]
Train steps ... :  15%|█▍        | 14580/100000 [3:53:16<13:54:10,  1.71it/s]
Train steps ... :  15%|█▍        | 14581/100000 [3:53:17<13:53:07,  1.71it/s]
Train steps ... :  15%|█▍        | 14582/100000 [3:53:17<13:53:55,  1.71it/s]
Train steps ... :  15%|█▍        | 14583/100000 [3:53:18<13:54:12,  1.71it/s]
Train steps ... :  15%|█▍        | 14584/100000 [3:53:19<13:52:09,  1.71it/s]
Train steps ... :  15%|█▍        | 14585/100000 [3:53:19<13:53:14,  1.71it/s]
Train steps ... :  15%|█▍        | 14586/100000 [3:53:20<13:53:56,  1.71it/s]
Train steps ... :  15%|█▍        | 14587/100000 [3:53:20<13:56:45,  1.70it/s]
Train steps ... :  15%|█▍        | 14588/100000 [3:53:21<13:52:35,  1.71it/s]
Train steps ... :  15%|█▍        | 14589/100000 [3:53:22<13:53:13,  1.71it/s]
Train steps ... :  15%|█▍        | 14590/100000 [3:53:22<13:52:26,  1.71it/s]
Train steps ... :  15%|█▍        | 14591/100000 [3:53:23<13:53:26,  1.71it/s]
Train steps ... :  15%|█▍        | 14592/100000 [3:53:23<13:53:35,  1.71it/s]
Train steps ... :  15%|█▍        | 14593/100000 [3:53:24<13:54:08,  1.71it/s]
Train steps ... :  15%|█▍        | 14594/100000 [3:53:24<13:53:30,  1.71it/s]
Train steps ... :  15%|█▍        | 14595/100000 [3:53:25<13:53:15,  1.71it/s]
Train steps ... :  15%|█▍        | 14596/100000 [3:53:26<13:54:48,  1.71it/s]
Train steps ... :  15%|█▍        | 14597/100000 [3:53:26<13:53:19,  1.71it/s]
Train steps ... :  15%|█▍        | 14598/100000 [3:53:27<13:53:42,  1.71it/s]
Train steps ... :  15%|█▍        | 14599/100000 [3:53:27<13:54:13,  1.71it/s]
Train steps ... :  15%|█▍        | 14600/100000 [3:53:28<13:53:49,  1.71it/s]Step... (14600 / 100000 | Loss: 1.0001633167266846, Learning Rate: 8.582914572864322e-05)
+
                                                                             
Step... (14600 / 100000 | Loss: 1.3940773010253906, Learning Rate: 8.582914572864322e-05)
+
Train steps ... :  15%|█▍        | 14600/100000 [3:53:28<13:53:49,  1.71it/s]
Train steps ... :  15%|█▍        | 14601/100000 [3:53:29<13:54:00,  1.71it/s]
Train steps ... :  15%|█▍        | 14602/100000 [3:53:29<13:53:33,  1.71it/s]
Train steps ... :  15%|█▍        | 14603/100000 [3:53:30<13:52:37,  1.71it/s]
Train steps ... :  15%|█▍        | 14604/100000 [3:53:30<13:52:06,  1.71it/s]
Train steps ... :  15%|█▍        | 14605/100000 [3:53:31<13:52:13,  1.71it/s]
Train steps ... :  15%|█▍        | 14606/100000 [3:53:31<13:52:07,  1.71it/s]
Train steps ... :  15%|█▍        | 14607/100000 [3:53:32<13:51:30,  1.71it/s]
Train steps ... :  15%|█▍        | 14608/100000 [3:53:33<13:52:50,  1.71it/s]
Train steps ... :  15%|█▍        | 14609/100000 [3:53:33<13:52:57,  1.71it/s]
Train steps ... :  15%|█▍        | 14610/100000 [3:53:34<13:52:52,  1.71it/s]
Train steps ... :  15%|█▍        | 14611/100000 [3:53:34<13:52:38,  1.71it/s]
Train steps ... :  15%|█▍        | 14612/100000 [3:53:35<13:52:10,  1.71it/s]
Train steps ... :  15%|█▍        | 14613/100000 [3:53:36<13:53:27,  1.71it/s]
Train steps ... :  15%|█▍        | 14614/100000 [3:53:36<13:56:01,  1.70it/s]
Train steps ... :  15%|█▍        | 14615/100000 [3:53:37<13:53:06,  1.71it/s]
Train steps ... :  15%|█▍        | 14616/100000 [3:53:37<13:51:59,  1.71it/s]
Train steps ... :  15%|█▍        | 14617/100000 [3:53:38<13:53:16,  1.71it/s]
Train steps ... :  15%|█▍        | 14618/100000 [3:53:38<13:52:34,  1.71it/s]
Train steps ... :  15%|█▍        | 14619/100000 [3:53:39<13:53:11,  1.71it/s]
Train steps ... :  15%|█▍        | 14620/100000 [3:53:40<13:53:20,  1.71it/s]
Train steps ... :  15%|█▍        | 14621/100000 [3:53:40<13:54:56,  1.70it/s]
Train steps ... :  15%|█▍        | 14622/100000 [3:53:41<13:52:26,  1.71it/s]
Train steps ... :  15%|█▍        | 14623/100000 [3:53:41<13:52:57,  1.71it/s]
Train steps ... :  15%|█▍        | 14624/100000 [3:53:42<13:53:09,  1.71it/s]
Train steps ... :  15%|█▍        | 14625/100000 [3:53:43<13:51:57,  1.71it/s]Step... (14625 / 100000 | Loss: 1.041774868965149, Learning Rate: 8.580402010050251e-05)
+
                                                                             
Step... (14625 / 100000 | Loss: 1.1219406127929688, Learning Rate: 8.580402010050251e-05)
+
Train steps ... :  15%|█▍        | 14625/100000 [3:53:43<13:51:57,  1.71it/s]
Train steps ... :  15%|█▍        | 14626/100000 [3:53:43<13:52:08,  1.71it/s]
Train steps ... :  15%|█▍        | 14627/100000 [3:53:44<13:53:04,  1.71it/s]
Train steps ... :  15%|█▍        | 14628/100000 [3:53:44<13:52:29,  1.71it/s]
Train steps ... :  15%|█▍        | 14629/100000 [3:53:45<13:54:22,  1.71it/s]
Train steps ... :  15%|█▍        | 14630/100000 [3:53:46<13:53:27,  1.71it/s]
Train steps ... :  15%|█▍        | 14631/100000 [3:53:46<13:53:52,  1.71it/s]
Train steps ... :  15%|█▍        | 14632/100000 [3:53:47<13:54:05,  1.71it/s]
Train steps ... :  15%|█▍        | 14633/100000 [3:53:47<13:54:03,  1.71it/s]
Train steps ... :  15%|█▍        | 14634/100000 [3:53:48<13:54:12,  1.71it/s]
Train steps ... :  15%|█▍        | 14635/100000 [3:53:48<13:53:33,  1.71it/s]
Train steps ... :  15%|█▍        | 14636/100000 [3:53:49<13:54:04,  1.71it/s]
Train steps ... :  15%|█▍        | 14637/100000 [3:53:50<13:52:20,  1.71it/s]
Train steps ... :  15%|█▍        | 14638/100000 [3:53:50<13:53:28,  1.71it/s]
Train steps ... :  15%|█▍        | 14639/100000 [3:53:51<13:52:33,  1.71it/s]
Train steps ... :  15%|█▍        | 14640/100000 [3:53:51<13:52:15,  1.71it/s]
Train steps ... :  15%|█▍        | 14641/100000 [3:53:52<13:52:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14642/100000 [3:53:53<13:55:58,  1.70it/s]
Train steps ... :  15%|█▍        | 14643/100000 [3:53:53<13:54:05,  1.71it/s]
Train steps ... :  15%|█▍        | 14644/100000 [3:53:54<13:54:02,  1.71it/s]
Train steps ... :  15%|█▍        | 14645/100000 [3:53:54<13:54:17,  1.71it/s]
Train steps ... :  15%|█▍        | 14646/100000 [3:53:55<13:53:36,  1.71it/s]
Train steps ... :  15%|█▍        | 14647/100000 [3:53:55<13:52:27,  1.71it/s]
Train steps ... :  15%|█▍        | 14648/100000 [3:53:56<13:52:55,  1.71it/s]
Train steps ... :  15%|█▍        | 14649/100000 [3:53:57<13:52:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14650/100000 [3:53:57<13:53:04,  1.71it/s]Step... (14650 / 100000 | Loss: 1.2183467149734497, Learning Rate: 8.577889447236181e-05)
+
                                                                             
Step... (14650 / 100000 | Loss: 1.167616844177246, Learning Rate: 8.577889447236181e-05)
+
Train steps ... :  15%|█▍        | 14650/100000 [3:53:58<13:53:04,  1.71it/s]
Train steps ... :  15%|█▍        | 14651/100000 [3:53:58<13:53:48,  1.71it/s]
Train steps ... :  15%|█▍        | 14652/100000 [3:53:58<13:51:12,  1.71it/s]
Train steps ... :  15%|█▍        | 14653/100000 [3:53:59<13:51:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14654/100000 [3:54:00<13:51:40,  1.71it/s]
Train steps ... :  15%|█▍        | 14655/100000 [3:54:00<13:52:21,  1.71it/s]
Train steps ... :  15%|█▍        | 14656/100000 [3:54:01<13:53:09,  1.71it/s]
Train steps ... :  15%|█▍        | 14657/100000 [3:54:01<13:54:18,  1.70it/s]
Train steps ... :  15%|█▍        | 14658/100000 [3:54:02<13:54:37,  1.70it/s]
Train steps ... :  15%|█▍        | 14659/100000 [3:54:03<13:53:11,  1.71it/s]
Train steps ... :  15%|█▍        | 14660/100000 [3:54:03<13:53:24,  1.71it/s]
Train steps ... :  15%|█▍        | 14661/100000 [3:54:04<13:53:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14662/100000 [3:54:04<13:53:48,  1.71it/s]
Train steps ... :  15%|█▍        | 14663/100000 [3:54:05<13:55:14,  1.70it/s]
Train steps ... :  15%|█▍        | 14664/100000 [3:54:05<13:53:39,  1.71it/s]
Train steps ... :  15%|█▍        | 14665/100000 [3:54:06<13:54:12,  1.70it/s]
Train steps ... :  15%|█▍        | 14666/100000 [3:54:07<13:56:10,  1.70it/s]
Train steps ... :  15%|█▍        | 14667/100000 [3:54:07<13:52:55,  1.71it/s]
Train steps ... :  15%|█▍        | 14668/100000 [3:54:08<13:52:15,  1.71it/s]
Train steps ... :  15%|█▍        | 14669/100000 [3:54:08<13:53:25,  1.71it/s]
Train steps ... :  15%|█▍        | 14670/100000 [3:54:09<13:54:02,  1.71it/s]
Train steps ... :  15%|█▍        | 14671/100000 [3:54:10<13:54:34,  1.70it/s]
Train steps ... :  15%|█▍        | 14672/100000 [3:54:10<13:54:02,  1.71it/s]
Train steps ... :  15%|█▍        | 14673/100000 [3:54:11<13:54:18,  1.70it/s]
Train steps ... :  15%|█▍        | 14674/100000 [3:54:11<13:53:11,  1.71it/s]
Train steps ... :  15%|█▍        | 14675/100000 [3:54:12<13:52:17,  1.71it/s]Step... (14675 / 100000 | Loss: 1.026749849319458, Learning Rate: 8.575376884422111e-05)
+
                                                                             
Step... (14675 / 100000 | Loss: 0.7940373420715332, Learning Rate: 8.575376884422111e-05)
+
Train steps ... :  15%|█▍        | 14675/100000 [3:54:12<13:52:17,  1.71it/s]
Train steps ... :  15%|█▍        | 14676/100000 [3:54:12<13:52:19,  1.71it/s]
Train steps ... :  15%|█▍        | 14677/100000 [3:54:13<13:52:22,  1.71it/s]
Train steps ... :  15%|█▍        | 14678/100000 [3:54:14<13:51:16,  1.71it/s]
Train steps ... :  15%|█▍        | 14679/100000 [3:54:14<13:51:44,  1.71it/s]
Train steps ... :  15%|█▍        | 14680/100000 [3:54:15<13:52:12,  1.71it/s]
Train steps ... :  15%|█▍        | 14681/100000 [3:54:15<13:51:33,  1.71it/s]
Train steps ... :  15%|█▍        | 14682/100000 [3:54:16<13:51:19,  1.71it/s]
Train steps ... :  15%|█▍        | 14683/100000 [3:54:17<13:51:39,  1.71it/s]
Train steps ... :  15%|█▍        | 14684/100000 [3:54:17<13:51:14,  1.71it/s]
Train steps ... :  15%|█▍        | 14685/100000 [3:54:18<13:52:46,  1.71it/s]
Train steps ... :  15%|█▍        | 14686/100000 [3:54:18<13:52:50,  1.71it/s]
Train steps ... :  15%|█▍        | 14687/100000 [3:54:19<13:52:10,  1.71it/s]
Train steps ... :  15%|█▍        | 14688/100000 [3:54:19<13:50:35,  1.71it/s]
Train steps ... :  15%|█▍        | 14689/100000 [3:54:20<13:51:11,  1.71it/s]
Train steps ... :  15%|█▍        | 14690/100000 [3:54:21<13:52:32,  1.71it/s]
Train steps ... :  15%|█▍        | 14691/100000 [3:54:21<13:52:15,  1.71it/s]
Train steps ... :  15%|█▍        | 14692/100000 [3:54:22<13:52:51,  1.71it/s]
Train steps ... :  15%|█▍        | 14693/100000 [3:54:22<13:52:47,  1.71it/s]
Train steps ... :  15%|█▍        | 14694/100000 [3:54:23<13:55:58,  1.70it/s]
Train steps ... :  15%|█▍        | 14695/100000 [3:54:24<13:54:40,  1.70it/s]
Train steps ... :  15%|█▍        | 14696/100000 [3:54:24<13:53:19,  1.71it/s]
Train steps ... :  15%|█▍        | 14697/100000 [3:54:25<13:53:01,  1.71it/s]
Train steps ... :  15%|█▍        | 14698/100000 [3:54:25<13:54:27,  1.70it/s]
Train steps ... :  15%|█▍        | 14699/100000 [3:54:26<13:54:54,  1.70it/s]
Train steps ... :  15%|█▍        | 14700/100000 [3:54:27<13:53:42,  1.71it/s]Step... (14700 / 100000 | Loss: 1.074779987335205, Learning Rate: 8.57286432160804e-05)
+
                                                                             
Step... (14700 / 100000 | Loss: 1.017433524131775, Learning Rate: 8.57286432160804e-05)
+
Train steps ... :  15%|█▍        | 14700/100000 [3:54:27<13:53:42,  1.71it/s]
Train steps ... :  15%|█▍        | 14701/100000 [3:54:27<13:51:43,  1.71it/s]
Train steps ... :  15%|█▍        | 14702/100000 [3:54:28<13:52:13,  1.71it/s]
Train steps ... :  15%|█▍        | 14703/100000 [3:54:28<13:54:16,  1.70it/s]
Train steps ... :  15%|█▍        | 14704/100000 [3:54:29<13:53:09,  1.71it/s]
Train steps ... :  15%|█▍        | 14705/100000 [3:54:29<13:53:25,  1.71it/s]
Train steps ... :  15%|█▍        | 14706/100000 [3:54:30<13:52:27,  1.71it/s]
Train steps ... :  15%|█▍        | 14707/100000 [3:54:31<13:53:25,  1.71it/s]
Train steps ... :  15%|█▍        | 14708/100000 [3:54:31<13:52:34,  1.71it/s]
Train steps ... :  15%|█▍        | 14709/100000 [3:54:32<13:52:25,  1.71it/s]
Train steps ... :  15%|█▍        | 14710/100000 [3:54:32<13:51:24,  1.71it/s]
Train steps ... :  15%|█▍        | 14711/100000 [3:54:33<13:53:37,  1.71it/s]
Train steps ... :  15%|█▍        | 14712/100000 [3:54:34<13:51:38,  1.71it/s]
Train steps ... :  15%|█▍        | 14713/100000 [3:54:34<13:51:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14714/100000 [3:54:35<13:50:55,  1.71it/s]
Train steps ... :  15%|█▍        | 14715/100000 [3:54:35<13:52:08,  1.71it/s]
Train steps ... :  15%|█▍        | 14716/100000 [3:54:36<13:52:37,  1.71it/s]
Train steps ... :  15%|█▍        | 14717/100000 [3:54:36<13:51:52,  1.71it/s]
Train steps ... :  15%|█▍        | 14718/100000 [3:54:37<13:53:13,  1.71it/s]
Train steps ... :  15%|█▍        | 14719/100000 [3:54:38<13:52:07,  1.71it/s]
Train steps ... :  15%|█▍        | 14720/100000 [3:54:38<13:55:56,  1.70it/s]
Train steps ... :  15%|█▍        | 14721/100000 [3:54:39<13:54:36,  1.70it/s]
Train steps ... :  15%|█▍        | 14722/100000 [3:54:39<13:53:26,  1.71it/s]
Train steps ... :  15%|█▍        | 14723/100000 [3:54:40<13:54:43,  1.70it/s]
Train steps ... :  15%|█▍        | 14724/100000 [3:54:41<13:53:40,  1.70it/s]
Train steps ... :  15%|█▍        | 14725/100000 [3:54:41<13:52:54,  1.71it/s]Step... (14725 / 100000 | Loss: 0.8452152013778687, Learning Rate: 8.570351758793971e-05)
+
                                                                             
Step... (14725 / 100000 | Loss: 1.1613314151763916, Learning Rate: 8.570351758793971e-05)
+
Train steps ... :  15%|█▍        | 14725/100000 [3:54:42<13:52:54,  1.71it/s]
Train steps ... :  15%|█▍        | 14726/100000 [3:54:42<13:53:24,  1.71it/s]
Train steps ... :  15%|█▍        | 14727/100000 [3:54:42<13:53:47,  1.70it/s]
Train steps ... :  15%|█▍        | 14728/100000 [3:54:43<13:53:32,  1.71it/s]
Train steps ... :  15%|█▍        | 14729/100000 [3:54:44<13:53:35,  1.70it/s]
Train steps ... :  15%|█▍        | 14730/100000 [3:54:44<13:52:04,  1.71it/s]
Train steps ... :  15%|█▍        | 14731/100000 [3:54:45<13:50:58,  1.71it/s]
Train steps ... :  15%|█▍        | 14732/100000 [3:54:45<13:54:26,  1.70it/s]
Train steps ... :  15%|█▍        | 14733/100000 [3:54:46<13:53:38,  1.70it/s]
Train steps ... :  15%|█▍        | 14734/100000 [3:54:46<13:53:16,  1.71it/s]
Train steps ... :  15%|█▍        | 14735/100000 [3:54:47<13:52:29,  1.71it/s]
Train steps ... :  15%|█▍        | 14736/100000 [3:54:48<13:52:44,  1.71it/s]
Train steps ... :  15%|█▍        | 14737/100000 [3:54:48<13:52:36,  1.71it/s]
Train steps ... :  15%|█▍        | 14738/100000 [3:54:49<13:54:06,  1.70it/s]
Train steps ... :  15%|█▍        | 14739/100000 [3:54:49<13:51:37,  1.71it/s]
Train steps ... :  15%|█▍        | 14740/100000 [3:54:50<13:50:41,  1.71it/s]
Train steps ... :  15%|█▍        | 14741/100000 [3:54:51<13:51:06,  1.71it/s]
Train steps ... :  15%|█▍        | 14742/100000 [3:54:51<13:52:32,  1.71it/s]
Train steps ... :  15%|█▍        | 14743/100000 [3:54:52<13:50:23,  1.71it/s]
Train steps ... :  15%|█▍        | 14744/100000 [3:54:52<13:51:48,  1.71it/s]
Train steps ... :  15%|█▍        | 14745/100000 [3:54:53<13:51:20,  1.71it/s]
Train steps ... :  15%|█▍        | 14746/100000 [3:54:53<13:50:56,  1.71it/s]
Train steps ... :  15%|█▍        | 14747/100000 [3:54:54<13:51:19,  1.71it/s]
Train steps ... :  15%|█▍        | 14748/100000 [3:54:55<13:51:05,  1.71it/s]
Train steps ... :  15%|█▍        | 14749/100000 [3:54:55<13:50:08,  1.71it/s]
Train steps ... :  15%|█▍        | 14750/100000 [3:54:56<13:51:35,  1.71it/s]Step... (14750 / 100000 | Loss: 1.1609761714935303, Learning Rate: 8.5678391959799e-05)
+
                                                                             
Step... (14750 / 100000 | Loss: 1.4512205123901367, Learning Rate: 8.5678391959799e-05)
+
Train steps ... :  15%|█▍        | 14750/100000 [3:54:56<13:51:35,  1.71it/s]
Train steps ... :  15%|█▍        | 14751/100000 [3:54:56<13:57:45,  1.70it/s]
Train steps ... :  15%|█▍        | 14752/100000 [3:54:57<13:56:03,  1.70it/s]
Train steps ... :  15%|█▍        | 14753/100000 [3:54:58<13:57:59,  1.70it/s]
Train steps ... :  15%|█▍        | 14754/100000 [3:54:58<13:53:32,  1.70it/s]
Train steps ... :  15%|█▍        | 14755/100000 [3:54:59<13:53:09,  1.71it/s]
Train steps ... :  15%|█▍        | 14756/100000 [3:54:59<13:52:16,  1.71it/s]
Train steps ... :  15%|█▍        | 14757/100000 [3:55:00<13:52:44,  1.71it/s]
Train steps ... :  15%|█▍        | 14758/100000 [3:55:01<13:51:23,  1.71it/s]
Train steps ... :  15%|█▍        | 14759/100000 [3:55:01<13:52:35,  1.71it/s]
Train steps ... :  15%|█▍        | 14760/100000 [3:55:02<13:51:34,  1.71it/s]
Train steps ... :  15%|█▍        | 14761/100000 [3:55:02<13:52:40,  1.71it/s]
Train steps ... :  15%|█▍        | 14762/100000 [3:55:03<13:52:02,  1.71it/s]
Train steps ... :  15%|█▍        | 14763/100000 [3:55:03<13:53:51,  1.70it/s]
Train steps ... :  15%|█▍        | 14764/100000 [3:55:04<13:52:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14765/100000 [3:55:05<13:52:33,  1.71it/s]
Train steps ... :  15%|█▍        | 14766/100000 [3:55:05<13:53:30,  1.70it/s]
Train steps ... :  15%|█▍        | 14767/100000 [3:55:06<13:53:56,  1.70it/s]
Train steps ... :  15%|█▍        | 14768/100000 [3:55:06<13:53:48,  1.70it/s]
Train steps ... :  15%|█▍        | 14769/100000 [3:55:07<13:53:13,  1.70it/s]
Train steps ... :  15%|█▍        | 14770/100000 [3:55:08<13:52:24,  1.71it/s]
Train steps ... :  15%|█▍        | 14771/100000 [3:55:08<13:52:12,  1.71it/s]
Train steps ... :  15%|█▍        | 14772/100000 [3:55:09<13:52:34,  1.71it/s]
Train steps ... :  15%|█▍        | 14773/100000 [3:55:09<13:51:38,  1.71it/s]
Train steps ... :  15%|█▍        | 14774/100000 [3:55:10<13:52:07,  1.71it/s]
Train steps ... :  15%|█▍        | 14775/100000 [3:55:10<13:52:21,  1.71it/s]Step... (14775 / 100000 | Loss: 1.2923059463500977, Learning Rate: 8.56532663316583e-05)
+
                                                                             
Step... (14775 / 100000 | Loss: 0.8966063261032104, Learning Rate: 8.56532663316583e-05)
+
Train steps ... :  15%|█▍        | 14775/100000 [3:55:11<13:52:21,  1.71it/s]
Train steps ... :  15%|█▍        | 14776/100000 [3:55:11<13:53:44,  1.70it/s]
Train steps ... :  15%|█▍        | 14777/100000 [3:55:12<13:54:22,  1.70it/s]
Train steps ... :  15%|█▍        | 14778/100000 [3:55:12<13:53:18,  1.70it/s]
Train steps ... :  15%|█▍        | 14779/100000 [3:55:13<13:55:32,  1.70it/s]
Train steps ... :  15%|█▍        | 14780/100000 [3:55:13<13:52:23,  1.71it/s]
Train steps ... :  15%|█▍        | 14781/100000 [3:55:14<13:52:35,  1.71it/s]
Train steps ... :  15%|█▍        | 14782/100000 [3:55:15<13:52:35,  1.71it/s]
Train steps ... :  15%|█▍        | 14783/100000 [3:55:15<13:52:59,  1.71it/s]
Train steps ... :  15%|█▍        | 14784/100000 [3:55:16<13:52:08,  1.71it/s]
Train steps ... :  15%|█▍        | 14785/100000 [3:55:16<13:51:07,  1.71it/s]
Train steps ... :  15%|█▍        | 14786/100000 [3:55:17<13:51:21,  1.71it/s]
Train steps ... :  15%|█▍        | 14787/100000 [3:55:18<13:52:08,  1.71it/s]
Train steps ... :  15%|█▍        | 14788/100000 [3:55:18<13:53:14,  1.70it/s]
Train steps ... :  15%|█▍        | 14789/100000 [3:55:19<13:53:54,  1.70it/s]
Train steps ... :  15%|█▍        | 14790/100000 [3:55:19<13:51:21,  1.71it/s]
Train steps ... :  15%|█▍        | 14791/100000 [3:55:20<13:52:38,  1.71it/s]
Train steps ... :  15%|█▍        | 14792/100000 [3:55:20<13:51:23,  1.71it/s]
Train steps ... :  15%|█▍        | 14793/100000 [3:55:21<13:52:41,  1.71it/s]
Train steps ... :  15%|█▍        | 14794/100000 [3:55:22<13:51:24,  1.71it/s]
Train steps ... :  15%|█▍        | 14795/100000 [3:55:22<13:53:12,  1.70it/s]
Train steps ... :  15%|█▍        | 14796/100000 [3:55:23<13:50:08,  1.71it/s]
Train steps ... :  15%|█▍        | 14797/100000 [3:55:23<13:51:23,  1.71it/s]
Train steps ... :  15%|█▍        | 14798/100000 [3:55:24<13:52:10,  1.71it/s]
Train steps ... :  15%|█▍        | 14799/100000 [3:55:25<13:52:09,  1.71it/s]
Train steps ... :  15%|█▍        | 14800/100000 [3:55:25<13:53:13,  1.70it/s]Step... (14800 / 100000 | Loss: 1.6163363456726074, Learning Rate: 8.562814070351759e-05)
+
                                                                             
Step... (14800 / 100000 | Loss: 1.0670719146728516, Learning Rate: 8.562814070351759e-05)
+
Train steps ... :  15%|█▍        | 14800/100000 [3:55:25<13:53:13,  1.70it/s]
Train steps ... :  15%|█▍        | 14801/100000 [3:55:26<13:53:52,  1.70it/s]
Train steps ... :  15%|█▍        | 14802/100000 [3:55:26<13:54:14,  1.70it/s]
Train steps ... :  15%|█▍        | 14803/100000 [3:55:27<13:53:22,  1.70it/s]
Train steps ... :  15%|█▍        | 14804/100000 [3:55:27<13:51:54,  1.71it/s]
Train steps ... :  15%|█▍        | 14805/100000 [3:55:28<13:51:24,  1.71it/s]
Train steps ... :  15%|█▍        | 14806/100000 [3:55:29<13:50:50,  1.71it/s]
Train steps ... :  15%|█▍        | 14807/100000 [3:55:29<13:51:47,  1.71it/s]
Train steps ... :  15%|█▍        | 14808/100000 [3:55:30<13:51:24,  1.71it/s]
Train steps ... :  15%|█▍        | 14809/100000 [3:55:30<13:51:56,  1.71it/s]
Train steps ... :  15%|█▍        | 14810/100000 [3:55:31<13:51:15,  1.71it/s]
Train steps ... :  15%|█▍        | 14811/100000 [3:55:32<13:51:52,  1.71it/s]
Train steps ... :  15%|█▍        | 14812/100000 [3:55:32<13:51:34,  1.71it/s]
Train steps ... :  15%|█▍        | 14813/100000 [3:55:33<13:51:00,  1.71it/s]
Train steps ... :  15%|█▍        | 14814/100000 [3:55:33<13:50:37,  1.71it/s]
Train steps ... :  15%|█▍        | 14815/100000 [3:55:34<13:51:49,  1.71it/s]
Train steps ... :  15%|█▍        | 14816/100000 [3:55:35<13:51:01,  1.71it/s]
Train steps ... :  15%|█▍        | 14817/100000 [3:55:35<13:50:50,  1.71it/s]
Train steps ... :  15%|█▍        | 14818/100000 [3:55:36<13:52:12,  1.71it/s]
Train steps ... :  15%|█▍        | 14819/100000 [3:55:36<13:54:47,  1.70it/s]
Train steps ... :  15%|█▍        | 14820/100000 [3:55:37<13:54:01,  1.70it/s]
Train steps ... :  15%|█▍        | 14821/100000 [3:55:37<13:50:57,  1.71it/s]
Train steps ... :  15%|█▍        | 14822/100000 [3:55:38<13:53:16,  1.70it/s]
Train steps ... :  15%|█▍        | 14823/100000 [3:55:39<13:52:04,  1.71it/s]
Train steps ... :  15%|█▍        | 14824/100000 [3:55:39<13:55:14,  1.70it/s]
Train steps ... :  15%|█▍        | 14825/100000 [3:55:40<13:53:26,  1.70it/s]Step... (14825 / 100000 | Loss: 1.264643907546997, Learning Rate: 8.560301507537689e-05)
+
                                                                             
Step... (14825 / 100000 | Loss: 0.811559796333313, Learning Rate: 8.560301507537689e-05)
+
Train steps ... :  15%|█▍        | 14825/100000 [3:55:40<13:53:26,  1.70it/s]
Train steps ... :  15%|█▍        | 14826/100000 [3:55:40<13:52:47,  1.70it/s]
Train steps ... :  15%|█▍        | 14827/100000 [3:55:41<13:54:34,  1.70it/s]
Train steps ... :  15%|█▍        | 14828/100000 [3:55:42<13:55:05,  1.70it/s]
Train steps ... :  15%|█▍        | 14829/100000 [3:55:42<13:53:07,  1.70it/s]
Train steps ... :  15%|█▍        | 14830/100000 [3:55:43<13:55:26,  1.70it/s]
Train steps ... :  15%|█▍        | 14831/100000 [3:55:43<13:54:14,  1.70it/s]
Train steps ... :  15%|█▍        | 14832/100000 [3:55:44<13:53:05,  1.70it/s]
Train steps ... :  15%|█▍        | 14833/100000 [3:55:44<13:53:33,  1.70it/s]
Train steps ... :  15%|█▍        | 14834/100000 [3:55:45<13:53:18,  1.70it/s]
Train steps ... :  15%|█▍        | 14835/100000 [3:55:46<13:53:24,  1.70it/s]
Train steps ... :  15%|█▍        | 14836/100000 [3:55:46<13:53:50,  1.70it/s]
Train steps ... :  15%|█▍        | 14837/100000 [3:55:47<13:52:29,  1.70it/s]
Train steps ... :  15%|█▍        | 14838/100000 [3:55:47<13:51:31,  1.71it/s]
Train steps ... :  15%|█▍        | 14839/100000 [3:55:48<13:51:35,  1.71it/s]
Train steps ... :  15%|█▍        | 14840/100000 [3:55:49<13:50:21,  1.71it/s]
Train steps ... :  15%|█▍        | 14841/100000 [3:55:49<13:51:39,  1.71it/s]
Train steps ... :  15%|█▍        | 14842/100000 [3:55:50<13:50:50,  1.71it/s]
Train steps ... :  15%|█▍        | 14843/100000 [3:55:50<13:51:41,  1.71it/s]
Train steps ... :  15%|█▍        | 14844/100000 [3:55:51<13:52:51,  1.70it/s]
Train steps ... :  15%|█▍        | 14845/100000 [3:55:52<13:51:29,  1.71it/s]
Train steps ... :  15%|█▍        | 14846/100000 [3:55:52<13:51:56,  1.71it/s]
Train steps ... :  15%|█▍        | 14847/100000 [3:55:53<13:52:22,  1.71it/s]
Train steps ... :  15%|█▍        | 14848/100000 [3:55:53<13:52:38,  1.70it/s]
Train steps ... :  15%|█▍        | 14849/100000 [3:55:54<13:51:31,  1.71it/s]
Train steps ... :  15%|█▍        | 14850/100000 [3:55:54<13:50:48,  1.71it/s]Step... (14850 / 100000 | Loss: 1.0770455598831177, Learning Rate: 8.557788944723618e-05)
+
                                                                             
Step... (14850 / 100000 | Loss: 1.3535263538360596, Learning Rate: 8.557788944723618e-05)
+
Train steps ... :  15%|█▍        | 14850/100000 [3:55:55<13:50:48,  1.71it/s]
Train steps ... :  15%|█▍        | 14851/100000 [3:55:55<13:50:55,  1.71it/s]
Train steps ... :  15%|█▍        | 14852/100000 [3:55:56<13:51:20,  1.71it/s]
Train steps ... :  15%|█▍        | 14853/100000 [3:55:56<13:52:38,  1.70it/s]
Train steps ... :  15%|█▍        | 14854/100000 [3:55:57<13:51:48,  1.71it/s]
Train steps ... :  15%|█▍        | 14855/100000 [3:55:57<13:51:43,  1.71it/s]
Train steps ... :  15%|█▍        | 14856/100000 [3:55:58<13:53:25,  1.70it/s]
Train steps ... :  15%|█▍        | 14857/100000 [3:55:59<13:52:56,  1.70it/s]
Train steps ... :  15%|█▍        | 14858/100000 [3:55:59<13:52:45,  1.70it/s]
Train steps ... :  15%|█▍        | 14859/100000 [3:56:00<13:53:29,  1.70it/s]
Train steps ... :  15%|█▍        | 14860/100000 [3:56:00<13:52:26,  1.70it/s]
Train steps ... :  15%|█▍        | 14861/100000 [3:56:01<13:51:50,  1.71it/s]
Train steps ... :  15%|█▍        | 14862/100000 [3:56:01<13:51:34,  1.71it/s]
Train steps ... :  15%|█▍        | 14863/100000 [3:56:02<13:52:58,  1.70it/s]
Train steps ... :  15%|█▍        | 14864/100000 [3:56:03<13:52:52,  1.70it/s]
Train steps ... :  15%|█▍        | 14865/100000 [3:56:03<13:54:37,  1.70it/s]
Train steps ... :  15%|█▍        | 14866/100000 [3:56:04<13:55:31,  1.70it/s]
Train steps ... :  15%|█▍        | 14867/100000 [3:56:04<13:52:14,  1.70it/s]
Train steps ... :  15%|█▍        | 14868/100000 [3:56:05<13:51:37,  1.71it/s]
Train steps ... :  15%|█▍        | 14869/100000 [3:56:06<13:50:40,  1.71it/s]
Train steps ... :  15%|█▍        | 14870/100000 [3:56:06<13:50:13,  1.71it/s]
Train steps ... :  15%|█▍        | 14871/100000 [3:56:07<13:49:39,  1.71it/s]
Train steps ... :  15%|█▍        | 14872/100000 [3:56:07<13:49:21,  1.71it/s]
Train steps ... :  15%|█▍        | 14873/100000 [3:56:08<13:51:30,  1.71it/s]
Train steps ... :  15%|█▍        | 14874/100000 [3:56:09<13:49:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14875/100000 [3:56:09<13:49:57,  1.71it/s]Step... (14875 / 100000 | Loss: 1.1478302478790283, Learning Rate: 8.555276381909548e-05)
+
                                                                             
Step... (14875 / 100000 | Loss: 1.0796821117401123, Learning Rate: 8.555276381909548e-05)
+
Train steps ... :  15%|█▍        | 14875/100000 [3:56:09<13:49:57,  1.71it/s]
Train steps ... :  15%|█▍        | 14876/100000 [3:56:10<13:53:22,  1.70it/s]
Train steps ... :  15%|█▍        | 14877/100000 [3:56:10<13:49:13,  1.71it/s]
Train steps ... :  15%|█▍        | 14878/100000 [3:56:11<13:50:31,  1.71it/s]
Train steps ... :  15%|█▍        | 14879/100000 [3:56:11<13:50:43,  1.71it/s]
Train steps ... :  15%|█▍        | 14880/100000 [3:56:12<13:50:58,  1.71it/s]
Train steps ... :  15%|█▍        | 14881/100000 [3:56:13<13:50:26,  1.71it/s]
Train steps ... :  15%|█▍        | 14882/100000 [3:56:13<13:51:13,  1.71it/s]
Train steps ... :  15%|█▍        | 14883/100000 [3:56:14<13:51:24,  1.71it/s]
Train steps ... :  15%|█▍        | 14884/100000 [3:56:14<13:52:43,  1.70it/s]
Train steps ... :  15%|█▍        | 14885/100000 [3:56:15<13:52:39,  1.70it/s]
Train steps ... :  15%|█▍        | 14886/100000 [3:56:16<13:54:53,  1.70it/s]
Train steps ... :  15%|█▍        | 14887/100000 [3:56:16<13:53:50,  1.70it/s]
Train steps ... :  15%|█▍        | 14888/100000 [3:56:17<13:53:08,  1.70it/s]
Train steps ... :  15%|█▍        | 14889/100000 [3:56:17<13:52:47,  1.70it/s]
Train steps ... :  15%|█▍        | 14890/100000 [3:56:18<13:53:42,  1.70it/s]
Train steps ... :  15%|█▍        | 14891/100000 [3:56:19<13:53:33,  1.70it/s]
Train steps ... :  15%|█▍        | 14892/100000 [3:56:19<13:51:19,  1.71it/s]
Train steps ... :  15%|█▍        | 14893/100000 [3:56:20<13:52:12,  1.70it/s]
Train steps ... :  15%|█▍        | 14894/100000 [3:56:20<13:51:55,  1.70it/s]
Train steps ... :  15%|█▍        | 14895/100000 [3:56:21<13:50:58,  1.71it/s]
Train steps ... :  15%|█▍        | 14896/100000 [3:56:21<13:50:27,  1.71it/s]
Train steps ... :  15%|█▍        | 14897/100000 [3:56:22<13:51:18,  1.71it/s]
Train steps ... :  15%|█▍        | 14898/100000 [3:56:23<13:52:42,  1.70it/s]
Train steps ... :  15%|█▍        | 14899/100000 [3:56:23<13:50:58,  1.71it/s]
Train steps ... :  15%|█▍        | 14900/100000 [3:56:24<13:48:10,  1.71it/s]Step... (14900 / 100000 | Loss: 1.5541729927062988, Learning Rate: 8.552763819095478e-05)
+
                                                                             
Step... (14900 / 100000 | Loss: 1.3846220970153809, Learning Rate: 8.552763819095478e-05)
+
Train steps ... :  15%|█▍        | 14900/100000 [3:56:24<13:48:10,  1.71it/s]
Train steps ... :  15%|█▍        | 14901/100000 [3:56:24<13:50:17,  1.71it/s]
Train steps ... :  15%|█▍        | 14902/100000 [3:56:25<13:50:57,  1.71it/s]
Train steps ... :  15%|█▍        | 14903/100000 [3:56:26<13:51:29,  1.71it/s]
Train steps ... :  15%|█▍        | 14904/100000 [3:56:26<13:50:08,  1.71it/s]
Train steps ... :  15%|█▍        | 14905/100000 [3:56:27<13:51:23,  1.71it/s]
Train steps ... :  15%|█▍        | 14906/100000 [3:56:27<13:51:17,  1.71it/s]
Train steps ... :  15%|█▍        | 14907/100000 [3:56:28<13:50:33,  1.71it/s]
Train steps ... :  15%|█▍        | 14908/100000 [3:56:28<13:50:27,  1.71it/s]
Train steps ... :  15%|█▍        | 14909/100000 [3:56:29<13:49:59,  1.71it/s]
Train steps ... :  15%|█▍        | 14910/100000 [3:56:30<13:50:43,  1.71it/s]
Train steps ... :  15%|█▍        | 14911/100000 [3:56:30<13:49:40,  1.71it/s]
Train steps ... :  15%|█▍        | 14912/100000 [3:56:31<13:51:50,  1.70it/s]
Train steps ... :  15%|█▍        | 14913/100000 [3:56:31<13:50:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14914/100000 [3:56:32<13:51:28,  1.71it/s]
Train steps ... :  15%|█▍        | 14915/100000 [3:56:33<13:50:01,  1.71it/s]
Train steps ... :  15%|█▍        | 14916/100000 [3:56:33<13:51:31,  1.71it/s]
Train steps ... :  15%|█▍        | 14917/100000 [3:56:34<13:51:01,  1.71it/s]
Train steps ... :  15%|█▍        | 14918/100000 [3:56:34<13:51:55,  1.70it/s]
Train steps ... :  15%|█▍        | 14919/100000 [3:56:35<13:50:49,  1.71it/s]
Train steps ... :  15%|█▍        | 14920/100000 [3:56:35<13:50:50,  1.71it/s]
Train steps ... :  15%|█▍        | 14921/100000 [3:56:36<13:50:28,  1.71it/s]
Train steps ... :  15%|█▍        | 14922/100000 [3:56:37<13:52:35,  1.70it/s]
Train steps ... :  15%|█▍        | 14923/100000 [3:56:37<13:50:58,  1.71it/s]
Train steps ... :  15%|█▍        | 14924/100000 [3:56:38<13:50:11,  1.71it/s]
Train steps ... :  15%|█▍        | 14925/100000 [3:56:38<13:52:22,  1.70it/s]Step... (14925 / 100000 | Loss: 1.2564408779144287, Learning Rate: 8.550251256281407e-05)
+
                                                                             
Step... (14925 / 100000 | Loss: 1.421814203262329, Learning Rate: 8.550251256281407e-05)
+
Train steps ... :  15%|█▍        | 14925/100000 [3:56:39<13:52:22,  1.70it/s]
Train steps ... :  15%|█▍        | 14926/100000 [3:56:39<13:51:30,  1.71it/s]
Train steps ... :  15%|█▍        | 14927/100000 [3:56:40<13:49:51,  1.71it/s]
Train steps ... :  15%|█▍        | 14928/100000 [3:56:40<13:50:48,  1.71it/s]
Train steps ... :  15%|█▍        | 14929/100000 [3:56:41<13:49:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14930/100000 [3:56:41<13:49:55,  1.71it/s]
Train steps ... :  15%|█▍        | 14931/100000 [3:56:42<13:50:06,  1.71it/s]
Train steps ... :  15%|█▍        | 14932/100000 [3:56:43<13:49:26,  1.71it/s]
Train steps ... :  15%|█▍        | 14933/100000 [3:56:43<13:52:02,  1.70it/s]
Train steps ... :  15%|█▍        | 14934/100000 [3:56:44<13:53:19,  1.70it/s]
Train steps ... :  15%|█▍        | 14935/100000 [3:56:44<13:52:50,  1.70it/s]
Train steps ... :  15%|█▍        | 14936/100000 [3:56:45<13:52:52,  1.70it/s]
Train steps ... :  15%|█▍        | 14937/100000 [3:56:45<13:51:34,  1.70it/s]
Train steps ... :  15%|█▍        | 14938/100000 [3:56:46<13:53:51,  1.70it/s]
Train steps ... :  15%|█▍        | 14939/100000 [3:56:47<13:52:02,  1.70it/s]
Train steps ... :  15%|█▍        | 14940/100000 [3:56:47<13:53:56,  1.70it/s]
Train steps ... :  15%|█▍        | 14941/100000 [3:56:48<13:53:38,  1.70it/s]
Train steps ... :  15%|█▍        | 14942/100000 [3:56:48<13:51:22,  1.71it/s]
Train steps ... :  15%|█▍        | 14943/100000 [3:56:49<13:52:26,  1.70it/s]
Train steps ... :  15%|█▍        | 14944/100000 [3:56:50<13:52:15,  1.70it/s]
Train steps ... :  15%|█▍        | 14945/100000 [3:56:50<13:52:38,  1.70it/s]
Train steps ... :  15%|█▍        | 14946/100000 [3:56:51<13:54:50,  1.70it/s]
Train steps ... :  15%|█▍        | 14947/100000 [3:56:51<13:52:35,  1.70it/s]
Train steps ... :  15%|█▍        | 14948/100000 [3:56:52<13:54:48,  1.70it/s]
Train steps ... :  15%|█▍        | 14949/100000 [3:56:53<13:53:22,  1.70it/s]
Train steps ... :  15%|█▍        | 14950/100000 [3:56:53<13:56:15,  1.70it/s]Step... (14950 / 100000 | Loss: 1.088191032409668, Learning Rate: 8.547738693467337e-05)
+
                                                                             
Step... (14950 / 100000 | Loss: 1.0348622798919678, Learning Rate: 8.547738693467337e-05)
+
Train steps ... :  15%|█▍        | 14950/100000 [3:56:53<13:56:15,  1.70it/s]
Train steps ... :  15%|█▍        | 14951/100000 [3:56:54<13:57:41,  1.69it/s]
Train steps ... :  15%|█▍        | 14952/100000 [3:56:54<13:52:35,  1.70it/s]
Train steps ... :  15%|█▍        | 14953/100000 [3:56:55<13:55:33,  1.70it/s]
Train steps ... :  15%|█▍        | 14954/100000 [3:56:55<13:53:03,  1.70it/s]
Train steps ... :  15%|█▍        | 14955/100000 [3:56:56<13:51:44,  1.70it/s]
Train steps ... :  15%|█▍        | 14956/100000 [3:56:57<13:53:28,  1.70it/s]
Train steps ... :  15%|█▍        | 14957/100000 [3:56:57<13:52:05,  1.70it/s]
Train steps ... :  15%|█▍        | 14958/100000 [3:56:58<13:52:10,  1.70it/s]
Train steps ... :  15%|█▍        | 14959/100000 [3:56:58<13:53:43,  1.70it/s]
Train steps ... :  15%|█▍        | 14960/100000 [3:56:59<13:50:16,  1.71it/s]
Train steps ... :  15%|█▍        | 14961/100000 [3:57:00<13:49:22,  1.71it/s]
Train steps ... :  15%|█▍        | 14962/100000 [3:57:00<13:51:50,  1.70it/s]
Train steps ... :  15%|█▍        | 14963/100000 [3:57:01<13:47:53,  1.71it/s]
Train steps ... :  15%|█▍        | 14964/100000 [3:57:01<13:48:13,  1.71it/s]
Train steps ... :  15%|█▍        | 14965/100000 [3:57:02<13:48:53,  1.71it/s]
Train steps ... :  15%|█▍        | 14966/100000 [3:57:02<13:50:14,  1.71it/s]
Train steps ... :  15%|█▍        | 14967/100000 [3:57:03<13:49:21,  1.71it/s]
Train steps ... :  15%|█▍        | 14968/100000 [3:57:04<13:49:05,  1.71it/s]
Train steps ... :  15%|█▍        | 14969/100000 [3:57:04<13:51:08,  1.71it/s]
Train steps ... :  15%|█▍        | 14970/100000 [3:57:05<13:49:56,  1.71it/s]
Train steps ... :  15%|█▍        | 14971/100000 [3:57:05<13:49:44,  1.71it/s]
Train steps ... :  15%|█▍        | 14972/100000 [3:57:06<13:51:20,  1.70it/s]
Train steps ... :  15%|█▍        | 14973/100000 [3:57:07<13:51:14,  1.70it/s]
Train steps ... :  15%|█▍        | 14974/100000 [3:57:07<13:50:29,  1.71it/s]
Train steps ... :  15%|█▍        | 14975/100000 [3:57:08<13:50:44,  1.71it/s]Step... (14975 / 100000 | Loss: 1.3349268436431885, Learning Rate: 8.545226130653267e-05)
+
                                                                             
Step... (14975 / 100000 | Loss: 1.1212999820709229, Learning Rate: 8.545226130653267e-05)
+
Train steps ... :  15%|█▍        | 14975/100000 [3:57:08<13:50:44,  1.71it/s]
Train steps ... :  15%|█▍        | 14976/100000 [3:57:08<13:49:49,  1.71it/s]
Train steps ... :  15%|█▍        | 14977/100000 [3:57:09<13:49:56,  1.71it/s]
Train steps ... :  15%|█▍        | 14978/100000 [3:57:10<13:49:45,  1.71it/s]
Train steps ... :  15%|█▍        | 14979/100000 [3:57:10<13:50:17,  1.71it/s]
Train steps ... :  15%|█▍        | 14980/100000 [3:57:11<13:50:52,  1.71it/s]
Train steps ... :  15%|█▍        | 14981/100000 [3:57:11<13:49:19,  1.71it/s]
Train steps ... :  15%|█▍        | 14982/100000 [3:57:12<13:51:08,  1.70it/s]
Train steps ... :  15%|█▍        | 14983/100000 [3:57:12<13:49:15,  1.71it/s]
Train steps ... :  15%|█▍        | 14984/100000 [3:57:13<13:49:38,  1.71it/s]
Train steps ... :  15%|█▍        | 14985/100000 [3:57:14<13:50:39,  1.71it/s]
Train steps ... :  15%|█▍        | 14986/100000 [3:57:14<13:50:38,  1.71it/s]
Train steps ... :  15%|█▍        | 14987/100000 [3:57:15<13:48:59,  1.71it/s]
Train steps ... :  15%|█▍        | 14988/100000 [3:57:15<13:53:18,  1.70it/s]
Train steps ... :  15%|█▍        | 14989/100000 [3:57:16<13:50:07,  1.71it/s]
Train steps ... :  15%|█▍        | 14990/100000 [3:57:17<13:49:14,  1.71it/s]
Train steps ... :  15%|█▍        | 14991/100000 [3:57:17<13:48:59,  1.71it/s]
Train steps ... :  15%|█▍        | 14992/100000 [3:57:18<13:48:50,  1.71it/s]
Train steps ... :  15%|█▍        | 14993/100000 [3:57:18<13:49:40,  1.71it/s]
Train steps ... :  15%|█▍        | 14994/100000 [3:57:19<13:49:24,  1.71it/s]
Train steps ... :  15%|█▍        | 14995/100000 [3:57:19<13:48:30,  1.71it/s]
Train steps ... :  15%|█▍        | 14996/100000 [3:57:20<13:48:09,  1.71it/s]
Train steps ... :  15%|█▍        | 14997/100000 [3:57:21<13:48:14,  1.71it/s]
Train steps ... :  15%|█▍        | 14998/100000 [3:57:21<13:50:04,  1.71it/s]
Train steps ... :  15%|█▍        | 14999/100000 [3:57:22<13:50:54,  1.70it/s]
Train steps ... :  15%|█▌        | 15000/100000 [3:57:22<13:47:52,  1.71it/s]Step... (15000 / 100000 | Loss: 1.4235131740570068, Learning Rate: 8.542713567839196e-05)
+
                                                                             
Step... (15000 / 100000 | Loss: 1.1313382387161255, Learning Rate: 8.542713567839196e-05)
+
Train steps ... :  15%|█▌        | 15000/100000 [3:57:23<13:47:52,  1.71it/s]06/17/2024 19:51:49 - INFO - accelerate.accelerator - Saving current state to ./checkpoint-15000-epoch-0
+06/17/2024 19:51:50 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/17/2024 19:51:53 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-15000-epoch-0/model.safetensors
+06/17/2024 19:51:53 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/17/2024 19:51:56 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-15000-epoch-0/model_1.safetensors
+06/17/2024 19:51:57 - INFO - accelerate.checkpointing - Optimizer state saved in checkpoint-15000-epoch-0/optimizer.bin
+06/17/2024 19:51:57 - INFO - accelerate.checkpointing - Scheduler state saved in checkpoint-15000-epoch-0/scheduler.bin
+06/17/2024 19:51:57 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in checkpoint-15000-epoch-0/sampler.bin
+06/17/2024 19:51:57 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in checkpoint-15000-epoch-0/sampler_1.bin
+06/17/2024 19:51:57 - INFO - accelerate.checkpointing - Sampler state for dataloader 2 saved in checkpoint-15000-epoch-0/sampler_2.bin
+06/17/2024 19:51:57 - INFO - accelerate.checkpointing - Random states saved in checkpoint-15000-epoch-0/random_states_0.pkl
+
+
  0%|          | 0/5 [00:00<?, ?it/s]
+
 20%|██        | 1/5 [01:48<07:13, 108.36s/it]
+
 40%|████      | 2/5 [02:24<03:18, 66.06s/it] 
+
 60%|██████    | 3/5 [02:25<01:12, 36.20s/it]
+
 80%|████████  | 4/5 [02:26<00:22, 22.16s/it]
+
100%|██████████| 5/5 [02:26<00:00, 14.41s/it]
100%|██████████| 5/5 [02:26<00:00, 29.36s/it]